© 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. 7-RESID-POST-AA
    11. 10335
    Prev
    Next
    INDEX
    Explanations

    code

    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
    Ah
    -0.07
     why
    -0.07
     inhibitor
    -0.07
    踪
    -0.07
    pling
    -0.07
     con
    -0.07
     bour
    -0.07
    中新
    -0.07
    Col
    -0.06
     Mt
    -0.06
    POSITIVE LOGITS
    ős
    0.07
    heten
    0.07
    랄
    0.07
     FileMode
    0.07
    Charset
    0.07
    يرا
    0.07
    _SECONDS
    0.06
    لاحظ
    0.06
    pto
    0.06
    .permissions
    0.06
    Activations Density 0.002%

    No Known Activations