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. 53892
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    soever
    -0.26
    纲
    -0.25
    rito
    -0.24
    æ¢ħèĬ±
    -0.24
    ç§£
    -0.24
    trs
    -0.24
    åIJĽ
    -0.24
    |min
    -0.24
     Kings
    -0.23
    .must
    -0.23
    POSITIVE LOGITS
    quate
    0.27
     Middleton
    0.26
    åħħè¶³çļĦ
    0.26
    -angle
    0.24
     passage
    0.24
    åĮħ
    0.24
    _GRE
    0.24
    orrent
    0.24
     Akron
    0.24
    ardy
    0.24
    Activations Density 1.769%

    No Known Activations

    This feature has no known activations.