© 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. 149894
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Mu
    -0.26
    Mu
    -0.25
    iect
    -0.25
    uje
    -0.24
    泺
    -0.24
    .fre
    -0.23
     Luca
    -0.23
    çīĩ
    -0.23
    æĬ±
    -0.23
     Escape
    -0.23
    POSITIVE LOGITS
    -terminal
    0.30
    尽头
    0.29
    scatter
    0.28
    apos
    0.27
    ths
    0.27
     quadrant
    0.25
    è¯
    0.24
     extinction
    0.23
    笤
    0.23
    CHED
    0.23
    Activations Density 0.298%

    No Known Activations

    This feature has no known activations.