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. 10347
    Prev
    Next
    INDEX
    Explanations

    code/technical documents

    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
     decom
    -0.28
    acr
    -0.26
    pipes
    -0.26
    asant
    -0.26
    æĦıå¤ĸ
    -0.25
    gist
    -0.25
    parse
    -0.25
    ineTransform
    -0.25
    ffer
    -0.25
    rr
    -0.24
    POSITIVE LOGITS
    ç¿»
    0.28
    IJľç´¢
    0.28
     Intervention
    0.27
    æ°§
    0.27
     audition
    0.27
    éĥģ
    0.26
    é¢Ĺç²Ĵ
    0.26
    Mass
    0.26
    ington
    0.26
    icut
    0.26
    Activations Density 0.002%

    No Known Activations