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. 53884
    Prev
    Next
    INDEX
    Explanations

    logged

    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
    anni
    -0.24
    aires
    -0.24
    RL
    -0.24
     Nations
    -0.23
     Cook
    -0.23
    orns
    -0.23
    éĽī
    -0.23
    年代
    -0.23
    RN
    -0.23
    RECT
    -0.23
    POSITIVE LOGITS
    eba
    0.28
    lem
    0.27
    ussion
    0.26
     Localization
    0.26
     quits
    0.26
    ç»ĵ
    0.26
    ä¸Ģè¾ĪåŃIJ
    0.25
    acad
    0.25
    roadcast
    0.24
    ä¿Ŀå®Ī
    0.24
    Activations Density 0.003%

    No Known Activations