© 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. 24342
    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
    rozen
    -0.33
     Hubb
    -0.29
    aki
    -0.27
    /Framework
    -0.27
    bomb
    -0.27
    ãģ¤ãģı
    -0.26
     grandfather
    -0.25
    lage
    -0.25
    inium
    -0.25
    沨
    -0.25
    POSITIVE LOGITS
    Furthermore
    0.26
     fencing
    0.25
    æ¯ıæĹ¥ç»ıæµİ
    0.25
     dette
    0.25
    Johnny
    0.25
    éĽģ
    0.25
    åĩºåĬ¨
    0.25
     Wor
    0.24
    cr
    0.24
    awn
    0.24
    Activations Density 0.026%

    No Known Activations

    This feature has no known activations.