© 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. 149805
    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
    åݨæĪ¿
    -0.27
    éĽĢ
    -0.26
    bat
    -0.26
     qualitative
    -0.25
    eshire
    -0.25
    åĬ³åĬ¨
    -0.25
    é¼ĵ
    -0.25
     painters
    -0.24
    çĻ¾åĪĨ
    -0.24
     labor
    -0.24
    POSITIVE LOGITS
    éĹ»
    0.29
    åħij
    0.28
    æĬľ
    0.27
    -grand
    0.26
    ооÑĢ
    0.26
    dis
    0.24
     cấp
    0.24
    ();)
    0.24
    oulos
    0.23
    åIJĪãĤı
    0.23
    Activations Density 0.158%

    No Known Activations

    This feature has no known activations.