© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 30-TRANSCODER-HP
    7. 95968
    Prev
    Next
    INDEX
    Explanations

    sum

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Education
    -0.27
     education
    -0.27
    æķĻèĤ²
    -0.26
    ä¸ĩæĪ·
    -0.26
    education
    -0.26
     bảng
    -0.26
    æ£ĢæŁ¥
    -0.25
    åıĹçIJĨ
    -0.25
    ucken
    -0.24
    æª¢æŁ¥
    -0.24
    POSITIVE LOGITS
     Sum
    0.38
    Sum
    0.35
    ç»Īç»ĵ
    0.35
     summ
    0.34
     sum
    0.33
    sum
    0.33
    summ
    0.33
     sums
    0.31
    -sum
    0.30
     SUM
    0.29
    Activations Density 0.884%

    No Known Activations