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. 0-TRANSCODER-HP
    4. 22
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_0.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.0.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ileo
    -0.30
    ·¨
    -0.27
    quirrel
    -0.25
    UNE
    -0.25
    byss
    -0.24
    ariat
    -0.24
    _zip
    -0.24
    ilogue
    -0.24
    .ne
    -0.24
    ypical
    -0.24
    POSITIVE LOGITS
    èĥĮéĿ¢
    0.30
    otes
    0.27
    [len
    0.25
     CLOCK
    0.25
     equival
    0.25
    æĽ´å¤ļ
    0.25
     defaultMessage
    0.25
    ker
    0.24
    èĥĮ
    0.24
     theater
    0.24
    Activations Density 3.986%

    No Known Activations