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. 4046
    Prev
    Next
    INDEX
    Explanations

    software installation and ammunition

    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
    è´£
    -0.28
    æĿĥçĽĬ
    -0.26
    IGIN
    -0.26
    enums
    -0.25
    ILTER
    -0.24
    acen
    -0.24
    许
    -0.24
    createCommand
    -0.24
    ruz
    -0.24
    éĢīæĭ©
    -0.24
    POSITIVE LOGITS
     Alonso
    0.27
    indsight
    0.27
    份
    0.26
    Mt
    0.26
     Twins
    0.26
    TRL
    0.25
     <<<
    0.25
     adults
    0.25
    _MAT
    0.24
    MF
    0.24
    Activations Density 0.006%

    No Known Activations