© 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. 22-TRANSCODER-HP
    7. 98707
    Prev
    Next
    INDEX
    Explanations

    And

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cụ
    -0.26
     specific
    -0.25
     puzzle
    -0.25
    SQLException
    -0.25
     Crop
    -0.24
    <>
    -0.24
     {.
    -0.23
     <|
    -0.23
    adamente
    -0.23
    /topic
    -0.23
    POSITIVE LOGITS
    åĨµ
    0.29
    æ³ģ
    0.29
    æĬĺ
    0.28
    itor
    0.27
    æĭ¬
    0.26
    itorio
    0.26
     Spears
    0.26
    annes
    0.25
    ários
    0.25
    ä¸Ģ个å¤ļ
    0.24
    Activations Density 0.002%

    No Known Activations