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. 24090
    Prev
    Next
    INDEX
    Explanations

    )

    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
    eki
    -0.33
    å¿ĥè¡Ģ
    -0.30
     HttpMethod
    -0.30
    ä¸įç»ı
    -0.28
     harass
    -0.26
    æľªç»ı
    -0.25
    åıijçĶŁåľ¨
    -0.25
    -LAST
    -0.24
    æľĪä¸ĭ
    -0.24
    azo
    -0.24
    POSITIVE LOGITS
    /../
    0.31
    ting
    0.30
    éģį
    0.28
    TING
    0.28
    ç»Ī身
    0.28
    æħ¢æħ¢çļĦ
    0.26
    gor
    0.26
    cs
    0.25
     min
    0.24
     Thing
    0.24
    Activations Density 0.001%

    No Known Activations