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. 24145
    Prev
    Next
    INDEX
    Explanations

    shirt

    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
    å¡ij
    -0.31
     plastic
    -0.27
    å¼ĢåıijåĮº
    -0.26
    第äºĮæī¹
    -0.25
     possessing
    -0.25
    èijĨ
    -0.24
    aba
    -0.24
    è²łè²¬
    -0.24
     mob
    -0.24
     punches
    -0.24
    POSITIVE LOGITS
    /*@
    0.29
    访
    0.26
     Herb
    0.25
    æŁ´
    0.25
    æ¾Ħæ¸ħ
    0.24
    Dependencies
    0.24
    Fi
    0.23
    ">%
    0.23
    tls
    0.23
    DCF
    0.23
    Activations Density 0.003%

    No Known Activations