© 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. 24032
    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
    boards
    -0.30
    otomy
    -0.27
    /on
    -0.26
    éļħ
    -0.26
     boards
    -0.25
    FML
    -0.25
    noinspection
    -0.25
    пÑĢавлÑı
    -0.24
    å¼Ĥ
    -0.24
    //{{
    -0.24
    POSITIVE LOGITS
    .PNG
    0.27
    ä»ĸå·²ç»ı
    0.26
    mes
    0.26
     build
    0.26
    åģļåĩºäºĨ
    0.25
    ç§ĥ
    0.25
    åIJ¸å¼ķ
    0.25
    åĢĴ
    0.25
    .unlock
    0.24
    .eth
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.