© 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. 24673
    Prev
    Next
    INDEX
    Explanations

    Raw data and code

    np_max-act · gemini-2.0-flash
    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
     Kun
    -0.27
    èĤ²
    -0.26
    ropol
    -0.26
     mon
    -0.26
    饯
    -0.25
    mon
    -0.25
    ç²¾ç¥ŀ
    -0.25
    æĺ¯ä¸Ģ
    -0.24
    èĴĻ
    -0.24
    antal
    -0.24
    POSITIVE LOGITS
    éľĦ
    0.25
    æ¯ķç«Ł
    0.25
     imports
    0.25
     spikes
    0.25
    clar
    0.25
    åĵ©
    0.24
    两æĿ¡
    0.24
     columns
    0.24
    è¿ĶåĽŀæIJľçĭIJ
    0.23
    åIJİæľŁ
    0.23
    Activations Density 1.067%

    No Known Activations