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. 72297
    Prev
    Next
    INDEX
    Explanations

    technical writing

    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
    lical
    -0.28
    coding
    -0.25
     h
    -0.25
    Legend
    -0.25
    alias
    -0.24
    Į¨
    -0.24
    éĢIJ
    -0.24
    bing
    -0.24
     drag
    -0.24
     d
    -0.23
    POSITIVE LOGITS
    WARE
    0.29
    hes
    0.28
    gne
    0.27
    AGO
    0.26
     irrespective
    0.26
    åı¯è¡Į
    0.25
    ি
    0.25
    gee
    0.24
    æĽĻ
    0.24
    opensource
    0.24
    Activations Density 0.001%

    No Known Activations