© 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. 149857
    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
    zug
    -0.30
    {text
    -0.24
    TRS
    -0.23
    CNT
    -0.23
    errick
    -0.23
    (graph
    -0.23
    xEA
    -0.23
    弶
    -0.22
    è¢«åĽ°
    -0.22
    _reload
    -0.22
    POSITIVE LOGITS
    è½»æĺĵ
    0.30
    pte
    0.29
     careful
    0.27
    åĮĢ
    0.27
    æµģåĬ¨
    0.26
    _State
    0.25
    å¾Īå¿«å°±
    0.25
    activité
    0.24
    gs
    0.24
    ç«ŀäºī
    0.23
    Activations Density 0.804%

    No Known Activations

    This feature has no known activations.