© 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. 11-RESID-POST-AA
    11. 1259
    Prev
    Next
    INDEX
    Explanations

    World

    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
    inated
    -0.07
     edit
    -0.07
     NUITKA
    -0.07
    rophe
    -0.07
    ounding
    -0.07
    苔
    -0.07
    ibaba
    -0.07
    �
    -0.06
    reuse
    -0.06
     disposit
    -0.06
    POSITIVE LOGITS
    .toFixed
    0.08
     يجب
    0.08
    明日
    0.07
    숵
    0.07
     Symposium
    0.07
     хочет
    0.07
    שים
    0.07
     chciał
    0.07
    (bg
    0.07
     Empire
    0.07
    Activations Density 0.003%

    No Known Activations