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. 23-RESID-POST-AA
    6. 247
    Prev
    Next
    INDEX
    Explanations

    source code

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .config
    -0.07
    jährige
    -0.07
     באותה
    -0.07
    eventType
    -0.07
    ocious
    -0.07
    �
    -0.07
     tüm
    -0.07
     período
    -0.07
     kiểu
    -0.07
    imestep
    -0.07
    POSITIVE LOGITS
    #######
    0.07
    Working
    0.07
    日常工作
    0.07
     Blind
    0.07
    #a
    0.07
    [cur
    0.07
    ’B
    0.07
     школь
    0.07
    FML
    0.06
    "{
    0.06
    Activations Density 0.001%

    No Known Activations