© 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. 111483
    Prev
    Next
    INDEX
    Explanations

    News articles

    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
    colour
    -0.28
    é²³
    -0.25
    ä¸Ģ个好çļĦ
    -0.25
     colours
    -0.25
     Hats
    -0.25
    /original
    -0.24
    æĪij们éľĢè¦ģ
    -0.24
    æĪijä»¬çŁ¥éģĵ
    -0.24
    eness
    -0.24
    å´ĩæĭľ
    -0.24
    POSITIVE LOGITS
    mps
    0.31
    æĪı
    0.29
    è°ĥéħį
    0.27
     ÑĦл
    0.27
    á»ijc
    0.26
    petition
    0.25
    dds
    0.25
    avin
    0.25
    mission
    0.25
    elage
    0.24
    Activations Density 0.008%

    No Known Activations