© 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. 129547
    Prev
    Next
    INDEX
    Explanations

    account login/signup information

    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
     vistas
    -0.29
     excell
    -0.27
    _styles
    -0.26
    å®ļåIJij
    -0.25
     VX
    -0.25
     QQ
    -0.24
    ä¸į代表
    -0.23
    missing
    -0.23
    çĶµè¯Ŀ
    -0.23
    åĽ¾çīĩ
    -0.23
    POSITIVE LOGITS
     guess
    0.27
     tph
    0.27
    -Pack
    0.26
    emain
    0.25
     gắn
    0.25
    é¾Ħ
    0.25
    guess
    0.24
    tright
    0.24
    æ¶ķ
    0.24
    ç§ijæĬĢ大åѦ
    0.24
    Activations Density 0.028%

    No Known Activations