© 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. 112633
    Prev
    Next
    INDEX
    Explanations

    (

    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
    å®ĺ
    -0.31
    %B
    -0.29
    次ä¼ļè®®
    -0.28
    ://%
    -0.27
    çļĦç¨ĭ度
    -0.26
    æĬľ
    -0.25
    次
    -0.25
     Hyde
    -0.25
    iasm
    -0.25
     decl
    -0.24
    POSITIVE LOGITS
    .ci
    0.26
     feu
    0.26
    ç»ıåħ¸çļĦ
    0.26
    ëŁī
    0.26
    以åıĬ
    0.24
    çĨŁçŁ¥
    0.24
    ittel
    0.24
    æĬķä¿Ŀ
    0.23
     és
    0.23
    elage
    0.23
    Activations Density 0.008%

    No Known Activations