© 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. 19-RESID-POST-AA
    11. 7452
    Prev
    Next
    INDEX
    Explanations

    parentheses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    新浪微博
    -0.08
     §§
    -0.07
    =localhost
    -0.07
     facts
    -0.07
     Redskins
    -0.07
    𝒪
    -0.07
    博主
    -0.07
    됀
    -0.07
    毯
    -0.07
    .ts
    -0.07
    POSITIVE LOGITS
    ested
    0.07
    望
    0.07
    amount
    0.07
    _ag
    0.06
    מהירות
    0.06
    ehicles
    0.06
     preca
    0.06
     Shay
    0.06
    텉
    0.06
    ปล
    0.06
    Activations Density 0.024%

    No Known Activations