© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 62255
    Prev
    Next
    INDEX
    Explanations

    technical, formal academic-language phrases—especially abstract noun forms, acronyms/parenthetical abbreviations, and methodology/process terminology typical of scientific writing.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    blogs
    -0.07
     commemorate
    -0.06
    Notification
    -0.06
     aquí
    -0.06
    卖场
    -0.06
    --*/↵
    -0.06
    aktion
    -0.06
     -/↵
    -0.06
    ubits
    -0.06
    onor
    -0.06
    POSITIVE LOGITS
    眈
    0.07
    融资租赁
    0.07
    	rs
    0.07
     /^[
    0.07
    Less
    0.07
    tbody
    0.06
    წ
    0.06
    挚
    0.06
    	es
    0.06
    _references
    0.06
    Activations Density 25.827%

    No Known Activations