© 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. 24-TRANSCODER-HP
    7. 150604
    Prev
    Next
    INDEX
    Explanations

    Non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pert
    -0.28
    azines
    -0.28
    -online
    -0.26
    -chart
    -0.25
    gers
    -0.25
     Online
    -0.24
    support
    -0.24
    amines
    -0.24
    å¿«ä¸ī
    -0.24
    online
    -0.23
    POSITIVE LOGITS
    åħ¨åľº
    0.30
    ç¿Ĵ
    0.30
    éĿ¢ç§¯
    0.28
    èĢķåľ°
    0.28
    ä¸ĩæĪ·
    0.28
    åIJĦæł·
    0.28
     lands
    0.28
    åĽ½åľŁ
    0.28
    æ¹ĸæ³Ĭ
    0.27
    ä½ıåĿĢ
    0.27
    Activations Density 0.110%

    No Known Activations