© 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. 96674
    Prev
    Next
    INDEX
    Explanations

    there

    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
    åѦä¼ļäºĨ
    -0.25
     INDIRECT
    -0.25
    缴æİ¥
    -0.25
    èĦ²
    -0.25
     langs
    -0.25
    Must
    -0.24
    ctal
    -0.24
    åı£æ°Ķ
    -0.24
    .ZERO
    -0.24
     Zero
    -0.24
    POSITIVE LOGITS
    就没æľī
    0.53
    æĺ¯æ²¡æľī
    0.52
    åĩłä¹İ没æľī
    0.52
     lack
    0.50
     keine
    0.49
    没æľīä»Ģä¹Ī
    0.49
     lacks
    0.49
     no
    0.48
    ä¸įåŃĺåľ¨
    0.46
    没æľī
    0.46
    Activations Density 0.899%

    No Known Activations