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. 1580
    Prev
    Next
    INDEX
    Explanations

    missions

    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
    .clf
    -0.25
     CHARSET
    -0.25
    -CN
    -0.25
    éϤ
    -0.24
     exerc
    -0.23
     DISCLAIMS
    -0.23
     recip
    -0.23
    館
    -0.23
     Nationals
    -0.23
    _CY
    -0.23
    POSITIVE LOGITS
    æµģæ°´
    0.27
    ä¿®åīª
    0.26
     ante
    0.26
    -degree
    0.25
    ÃŁen
    0.25
    íĸ¥
    0.25
    å¿Ĺ强
    0.25
     reach
    0.25
     map
    0.24
    izen
    0.24
    Activations Density 0.002%

    No Known Activations