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. 10321
    Prev
    Next
    INDEX
    Explanations

    Tess

    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
    æĿĥçĽĬ
    -0.33
     milit
    -0.27
    å̾æĸľ
    -0.27
     Infer
    -0.26
    æĿĥ
    -0.26
    instein
    -0.24
     bids
    -0.24
     reimburse
    -0.24
     cuts
    -0.23
     пока
    -0.23
    POSITIVE LOGITS
    æĺ¯ä½ł
    0.30
     ;↵↵
    0.26
    ibox
    0.26
    TagName
    0.26
    ificant
    0.26
     ;č↵
    0.26
    č↵        č↵
    0.25
     ;č↵č↵
    0.25
    ogi
    0.25
     __________________↵↵
    0.25
    Activations Density 0.003%

    No Known Activations