© 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. 98150
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     cere
    -0.26
    ifndef
    -0.24
    askan
    -0.23
    ç½ijç»ľä¼łæĴŃ
    -0.23
    æ³Į
    -0.23
     part
    -0.22
    theon
    -0.22
    -order
    -0.22
    .Undef
    -0.22
    å±ħ
    -0.21
    POSITIVE LOGITS
    ä¸Ģçľ¼
    0.28
    insky
    0.26
    è¯Ŀ说
    0.25
    òa
    0.23
    aux
    0.23
    æ¨¡æł·
    0.23
    éķ¿çĽ¸
    0.23
    æ¸ħæ¥ļ
    0.23
    Vy
    0.23
    lov
    0.23
    Activations Density 0.088%

    No Known Activations

    This feature has no known activations.