© 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. 112240
    Prev
    Next
    INDEX
    Explanations

    ested

    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
    axed
    -0.30
    æµ£
    -0.26
    -Christian
    -0.25
     queryInterface
    -0.25
    ushman
    -0.25
    arest
    -0.24
     Diablo
    -0.24
    第ä¸Ģ家
    -0.23
    ç®
    -0.23
    æĺŁæľŁ
    -0.23
    POSITIVE LOGITS
     NOTES
    0.29
    åĽ´çĿĢ
    0.25
    æĵł
    0.24
    isure
    0.24
    åIJİèĢħ
    0.24
     füh
    0.24
    èĢģå¸Ī们
    0.23
     réserve
    0.23
    åĪ»çĶ»
    0.23
    accuracy
    0.23
    Activations Density 0.003%

    No Known Activations