© 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. 149627
    Prev
    Next
    INDEX
    Explanations

    mend

    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
    éĽªèĬ±
    -0.26
    gest
    -0.26
    èIJ¥åķĨ
    -0.26
    diff
    -0.25
    exels
    -0.24
    鼶ç¢İ
    -0.24
    æݸ
    -0.24
     Diff
    -0.24
     desktop
    -0.23
    强èĢħ
    -0.23
    POSITIVE LOGITS
    apatkan
    0.27
    æķ´é½IJ
    0.27
    ç¥ī
    0.26
     vigor
    0.25
    LER
    0.24
    æľ¬æĬ¥è®°èĢħ
    0.24
    endez
    0.24
    oreal
    0.24
     presumption
    0.24
    ement
    0.24
    Activations Density 0.803%

    No Known Activations