© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 45751
    Prev
    Next
    INDEX
    Explanations

    [

    np_max-act · gemini-2.0-flash
    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
     Delete
    -0.07
     declines
    -0.07
     médico
    -0.07
    pływ
    -0.07
     órgão
    -0.07
     była
    -0.07
    ementia
    -0.07
     וכך
    -0.07
    ła
    -0.07
    Va
    -0.07
    POSITIVE LOGITS
     bunch
    0.07
     тыся
    0.07
     fighter
    0.07
    _bank
    0.07
    孙
    0.06
     עוב
    0.06
     tons
    0.06
     Beginner
    0.06
    榛
    0.06
     artificial
    0.06
    Activations Density 0.003%

    No Known Activations