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. 1740
    Prev
    Next
    INDEX
    Explanations

    0 or 9

    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
    usty
    -0.28
    ä¸Ģä¸ĸ
    -0.27
    .addValue
    -0.27
    è½Ń
    -0.27
     dah
    -0.26
    Êĥ
    -0.25
    æĬķè¯ī
    -0.25
    åģĩ
    -0.24
    setProperty
    -0.24
    eworld
    -0.24
    POSITIVE LOGITS
     renamed
    0.28
    Named
    0.27
    ç»Ħ
    0.27
     remake
    0.26
    æijĩ
    0.26
    dfs
    0.25
    ä¼łç»Łäº§ä¸ļ
    0.25
     Reco
    0.25
     pand
    0.25
    comes
    0.25
    Activations Density 0.006%

    No Known Activations