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. 54511
    Prev
    Next
    INDEX
    Explanations

    although

    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
    pile
    -0.30
    åħģ
    -0.28
    (Channel
    -0.26
    -strokes
    -0.25
    unky
    -0.25
    arak
    -0.25
    attered
    -0.24
    ÑĪки
    -0.24
    åįķåĵģ
    -0.24
     Rene
    -0.24
    POSITIVE LOGITS
    rig
    0.29
    ä¸Ĭåįĩ
    0.28
    sworth
    0.27
    inherits
    0.27
     interface
    0.26
    nos
    0.26
    interface
    0.25
    OOM
    0.24
    hum
    0.24
    vos
    0.24
    Activations Density 0.078%

    No Known Activations