© 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 EvalsExportsinterp-engineNEWAPI 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. 11919
    Prev
    Next
    INDEX
    Explanations

    blog categories/tags

    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
     답
    -0.07
    纪录
    -0.07
     tomato
    -0.07
    ="@
    -0.07
    speaker
    -0.07
    .mb
    -0.07
     palavra
    -0.07
     cycling
    -0.06
     Québec
    -0.06
     tokens
    -0.06
    POSITIVE LOGITS
    岨
    0.07
    SOEVER
    0.07
    mówi
    0.07
    .Fatalf
    0.07
    ⍋
    0.06
    Services
    0.06
     medications
    0.06
    join
    0.06
    ᾦ
    0.06
    entry
    0.06
    Activations Density 0.001%

    No Known Activations