© 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. 27-TRANSCODER-HP
    7. 9364
    Prev
    Next
    INDEX
    Explanations

    coding/technical documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osite
    -0.29
    éĿłçĿĢ
    -0.29
    åĽ´ç»ķ
    -0.29
    è¾¾ä¸įåĪ°
    -0.28
    ounder
    -0.28
    两边
    -0.28
    ä¾ĿéĿł
    -0.27
    ä¸įåĩºæĿ¥
    -0.26
    声åĵį
    -0.26
    åij¨å¹´
    -0.26
    POSITIVE LOGITS
     even
    0.27
    uns
    0.27
     tel
    0.27
    z
    0.27
     Walters
    0.26
     overflow
    0.25
     budding
    0.25
    éģĵ
    0.24
    ermen
    0.24
    iff
    0.24
    Activations Density 0.890%

    No Known Activations