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

    Neuronpedia

    Jacobian LensNEW
    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. 11-RESID-POST-AA
    11. 65602
    Prev
    Next
    INDEX
    Explanations

    safety reports

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    汽车
    -0.08
    (TR
    -0.08
     dairy
    -0.07
     Amph
    -0.06
    にて
    -0.06
    _NAV
    -0.06
    虹
    -0.06
     ком
    -0.06
    _]
    -0.06
     enjoyable
    -0.06
    POSITIVE LOGITS
    inka
    0.07
    >".$
    0.07
     Raised
    0.07
    不要
    0.07
     реши
    0.07
     regenerated
    0.07
    urate
    0.06
    olation
    0.06
    longleftrightarrow
    0.06
    дают
    0.06
    Activations Density 0.114%

    No Known Activations