© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 24-TRANSCODER-HP
    7. 149324
    Prev
    Next
    INDEX
    Explanations

    electromechanical systems

    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
    Negative Logits
    Frames
    -0.29
    rest
    -0.28
    .Binding
    -0.27
     frames
    -0.26
     framing
    -0.26
     territorial
    -0.26
    iders
    -0.25
     rest
    -0.25
     Frames
    -0.25
    _frames
    -0.25
    POSITIVE LOGITS
    ä½ľèĢħæľ¬äºº
    0.28
    æľ¬äºº
    0.25
    eenth
    0.24
     Samoa
    0.24
    rtc
    0.23
    é²ŀ
    0.23
    èĪIJ
    0.23
    ÑĢон
    0.23
    íݸ
    0.23
    羣å®ŀæĢ§
    0.23
    Activations Density 0.038%

    No Known Activations