© 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. 129428
    Prev
    Next
    INDEX
    Explanations

    name

    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
    rippling
    -0.29
    roz
    -0.26
    é£İåIJ¹
    -0.25
    ä¸įæĸ¹ä¾¿
    -0.25
    åľ¨åħ¨çIJĥ
    -0.25
    olini
    -0.25
    解å¼Ģ
    -0.25
    tractive
    -0.24
    åĨįæĿ¥
    -0.24
    çĩĶ
    -0.24
    POSITIVE LOGITS
    outh
    0.33
    ye
    0.27
    ç¯
    0.26
    æ¹¾åĮº
    0.25
    à¹ģà¸Ļ
    0.25
    ild
    0.24
     chắc
    0.23
     Yeah
    0.23
    _Main
    0.23
    Declaration
    0.23
    Activations Density 0.008%

    No Known Activations