© 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. 87646
    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
    èģĭ
    -0.27
    èĥ¶
    -0.26
     Sabbath
    -0.25
    èĸ¯
    -0.25
    rient
    -0.25
    æģ¬
    -0.25
    QU
    -0.24
    赶快
    -0.23
     Ellen
    -0.23
    趣
    -0.23
    POSITIVE LOGITS
    iales
    0.27
    hosts
    0.23
    ä¸Ģé¢Ĺ
    0.23
     sÅĤow
    0.23
     Hose
    0.23
    contre
    0.23
    ç»Ļ她
    0.23
     /*!<
    0.23
    åĹĵåŃIJ
    0.22
    езн
    0.22
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.