© 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. 130383
    Prev
    Next
    INDEX
    Explanations

    technical/scientific text

    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
    ês
    -0.27
     rhet
    -0.25
     unins
    -0.25
    ât
    -0.25
    åij¨å¹´
    -0.25
     belie
    -0.24
    æī«çłģ
    -0.24
    challenge
    -0.24
    -widgets
    -0.24
    ç²¢
    -0.24
    POSITIVE LOGITS
    åľ¨ä¸Ĭæµ·
    0.27
    åľ¨æ¸¸æĪıä¸Ń
    0.26
     in
    0.26
    åľ¨ä¸ŃåĽ½
    0.26
    çŃĭ
    0.26
    ivate
    0.26
    .setParent
    0.26
    ë°ĺ
    0.26
    åľ¨åħ¨åĽ½
    0.25
    å®ī
    0.25
    Activations Density 0.010%

    No Known Activations