© 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. 24003
    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
    quences
    -0.29
    串
    -0.27
    åºıåĪĹ
    -0.25
    åįıè°ĥ
    -0.25
    sequences
    -0.25
    èŀįåIJĪ
    -0.24
    ì§IJ
    -0.24
    纸ä¸Ĭ
    -0.24
     prevent
    -0.23
     analyses
    -0.23
    POSITIVE LOGITS
     tastes
    0.29
    豫
    0.29
    é¢ĦæĬ¥
    0.28
    earned
    0.28
    .Generated
    0.25
    .createComponent
    0.25
     earned
    0.25
     fortune
    0.25
    bove
    0.25
     prediction
    0.24
    Activations Density 0.010%

    No Known Activations

    This feature has no known activations.