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. 1554
    Prev
    Next
    INDEX
    Explanations

    Abbreviations

    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
    ificant
    -0.28
     little
    -0.27
     figure
    -0.26
    ä½ĵç³»
    -0.26
    itch
    -0.26
    //===
    -0.25
     pickle
    -0.25
    è¿ĺ没
    -0.25
    scriber
    -0.25
    kin
    -0.24
    POSITIVE LOGITS
    uci
    0.27
    -author
    0.27
    ibly
    0.27
     ("<
    0.25
    æĬij
    0.25
    pisa
    0.24
    apis
    0.24
    æªĹ
    0.24
     Público
    0.23
    oda
    0.23
    Activations Density 0.783%

    No Known Activations