© 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. 97988
    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
    è´´
    -0.30
    “All
    -0.24
    UMAN
    -0.24
    è¡°
    -0.24
    ptic
    -0.24
    Fel
    -0.24
    translator
    -0.24
    pd
    -0.23
    _tbl
    -0.23
    “One
    -0.23
    POSITIVE LOGITS
    DetailsService
    0.29
    classCallCheck
    0.26
    onta
    0.26
     ministers
    0.26
    ä¾Ŀæ³ķ追究
    0.25
    _include
    0.24
    ä»ħ代表
    0.24
    iÄĻ
    0.23
    ä¼Ĭæĸ¯
    0.23
     deduct
    0.23
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.