© 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. 130239
    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
    Vectorizer
    -0.25
    å¼Ģå·¥
    -0.24
    verage
    -0.24
     Inches
    -0.23
    odesk
    -0.23
    åįģåĩłå¹´
    -0.23
    åĩłå¹´
    -0.22
    ä¸įå®ļ
    -0.22
    pected
    -0.22
    主ä¸ļ
    -0.22
    POSITIVE LOGITS
    æ³³
    0.27
    è§Ħ
    0.26
     Fly
    0.26
    RITE
    0.24
    dig
    0.23
     uniquely
    0.23
    -window
    0.23
    çª
    0.22
     floats
    0.22
    ï¿
    0.21
    Activations Density 0.052%

    No Known Activations

    This feature has no known activations.