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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 11-TRANSCODER-HP
    4. 54531
    Prev
    Next
    INDEX
    Explanations

    dots

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_11.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.11.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     infl
    -0.29
    egers
    -0.28
    è§£æĶ¾
    -0.26
     Locator
    -0.26
     compensate
    -0.26
    享èªī
    -0.25
    asename
    -0.25
     unheard
    -0.24
    åħ¨çIJĥåĮĸ
    -0.24
     yourselves
    -0.24
    POSITIVE LOGITS
    ols
    0.28
    (cols
    0.25
    cols
    0.25
    iments
    0.25
     timetable
    0.24
     cols
    0.24
    IPS
    0.24
     ming
    0.24
    Appointment
    0.23
    交ç»ĩ
    0.23
    Activations Density 0.054%

    No Known Activations