© 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. 7-RESID-POST-AA
    11. 57124
    Prev
    Next
    INDEX
    Explanations

    illness

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ä
    -0.08
     HA
    -0.07
    復
    -0.07
     ra
    -0.07
    Jur
    -0.07
    Â
    -0.07
    finish
    -0.07
     Newly
    -0.07
    复
    -0.07
    ₴
    -0.07
    POSITIVE LOGITS
    (DWORD
    0.07
    柩
    0.07
    엠
    0.07
    abra
    0.07
    /about
    0.07
    淡淡
    0.07
     preamble
    0.07
     AOL
    0.07
     Plumbing
    0.07
     dildo
    0.07
    Activations Density 0.087%

    No Known Activations