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. 130047
    Prev
    Next
    INDEX
    Explanations

    fight

    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
    amed
    -0.29
    ULE
    -0.25
     mixture
    -0.24
    åħ±è®¡
    -0.24
    AME
    -0.24
     breeding
    -0.24
    rott
    -0.24
    iba
    -0.24
     mixed
    -0.24
    XYZ
    -0.24
    POSITIVE LOGITS
    ref
    0.26
    /ref
    0.26
    quirer
    0.26
    ret
    0.26
    RET
    0.25
    æĻļ
    0.24
    referrer
    0.24
     spinach
    0.24
    èµ·çĤ¹
    0.24
    Ret
    0.23
    Activations Density 0.000%

    No Known Activations