© 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. 111383
    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
    ENCY
    -0.28
    ment
    -0.27
    EMENT
    -0.25
     bet
    -0.24
     Merry
    -0.24
    odash
    -0.24
    Fcn
    -0.24
    ucz
    -0.24
    _bt
    -0.23
    INCREMENT
    -0.23
    POSITIVE LOGITS
    åŁİå¸ĤçļĦ
    0.29
    itsu
    0.27
    å°ĸ
    0.26
    ä½ľä¸ºä¸Ģç§į
    0.25
    éĻ·
    0.25
     вн
    0.25
    éĩijå¥ĸ
    0.25
    èĭĽ
    0.25
    ä»ģ
    0.25
     nil
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.