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. 21674
    Prev
    Next
    INDEX
    Explanations

    Medicine/Health

    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
    æĺ¯ä¸įæĺ¯
    -0.29
    ifter
    -0.27
    ANTED
    -0.27
    æĺ¯åIJ¦
    -0.27
     realizing
    -0.26
    изм
    -0.26
     realization
    -0.26
    iterr
    -0.25
     realize
    -0.25
    erty
    -0.24
    POSITIVE LOGITS
    iw
    0.26
    __)↵
    0.25
     Sutton
    0.25
     hashing
    0.25
     shadows
    0.24
     walks
    0.24
    rights
    0.24
     conform
    0.23
     Ub
    0.23
    翼
    0.23
    Activations Density 0.001%

    No Known Activations