© 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. 15-RESID-POST-AA
    11. 117982
    Prev
    Next
    INDEX
    Explanations

    Code/error messages

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    憭
    -0.07
    well
    -0.06
    渰
    -0.06
     listens
    -0.06
    (conn
    -0.06
    doc
    -0.06
    linkplain
    -0.06
    cnt
    -0.06
    🏷
    -0.06
    declspec
    -0.06
    POSITIVE LOGITS
     Thủ
    0.09
    تكن
    0.07
     aqu
    0.07
    إصابة
    0.07
    .Graph
    0.07
     subsidized
    0.07
     рождения
    0.07
    محافظ
    0.07
    .Glide
    0.07
     bệnh
    0.07
    Activations Density 0.039%

    No Known Activations