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. 7-TRANSCODER-HP
    4. 98036
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_7.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.7.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĽ¸äº²
    -0.27
    ansi
    -0.26
    isce
    -0.26
    éĴĵ
    -0.25
    æħ°éĹ®
    -0.25
    iola
    -0.24
    æĢ»éĺŁ
    -0.24
    åıĹå½±åĵį
    -0.24
    ä¸İæĹ¶
    -0.24
    ough
    -0.24
    POSITIVE LOGITS
     cabo
    0.26
    -ra
    0.24
     circulating
    0.24
    packing
    0.23
    éĩijå±±
    0.23
    /provider
    0.23
    åı
    0.23
    æĭīèIJ¨
    0.23
     Tops
    0.23
    riting
    0.23
    Activations Density 0.000%

    No Known Activations