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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 19-RESID-POST-AA
    6. 59536
    Prev
    Next
    INDEX
    Explanations

    Decreases over time

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    团伙
    -0.07
    作用
    -0.07
    意識
    -0.07
    ísimo
    -0.07
    人の
    -0.07
    Healthy
    -0.07
     représente
    -0.07
    毛巾
    -0.06
    垿
    -0.06
    动机
    -0.06
    POSITIVE LOGITS
     parentNode
    0.07
     #%
    0.07
    ca
    0.07
    缓
    0.06
    println
    0.06
     gardens
    0.06
    .pet
    0.06
    while
    0.06
    铮
    0.06
    [k
    0.06
    Activations Density 0.023%

    No Known Activations