© 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. 23-TRANSCODER-HP
    7. 25123
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    裱
    -0.29
    _ctxt
    -0.28
    .addElement
    -0.27
    inction
    -0.25
     agony
    -0.25
    lä
    -0.25
    .`
    -0.25
    第ä¸īèĬĤ
    -0.24
     afternoon
    -0.24
    è°°
    -0.23
    POSITIVE LOGITS
    /cli
    0.27
    éģĵ
    0.27
    çĶŁæ´»æĸ¹å¼ı
    0.25
    èĢĮå·²
    0.25
    é£ŀ
    0.25
    mentions
    0.25
    asti
    0.25
    éĵĥ
    0.25
    ![
    0.25
    etto
    0.25
    Activations Density 0.031%

    No Known Activations

    This feature has no known activations.