Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 16460
    Prev
    Next
    INDEX
    Explanations

    budget

    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
    (dm
    -0.08
     הנ
    -0.07
    למת
    -0.07
    atype
    -0.07
    可爱
    -0.07
     tst
    -0.07
    vature
    -0.07
    ⍣
    -0.07
    深化改革
    -0.07
    🌅
    -0.07
    POSITIVE LOGITS
    FileStream
    0.07
    �
    0.07
     say
    0.07
    iation
    0.07
    oidal
    0.07
    表
    0.07
     singers
    0.06
     used
    0.06
     saying
    0.06
    Paragraph
    0.06
    Activations Density 0.011%

    No Known Activations