© 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. 98780
    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
    zag
    -0.27
    	operator
    -0.26
    TemplateName
    -0.26
    份
    -0.25
     sick
    -0.25
    ëĿ½
    -0.24
    äº
    -0.24
    uiten
    -0.24
    é¦ĸ
    -0.24
    æľĢç»Ī
    -0.24
    POSITIVE LOGITS
    oxy
    0.31
     dispos
    0.28
    æ°ĺ
    0.27
    erd
    0.27
     DISP
    0.26
    ç¬Ļ
    0.26
     disposing
    0.26
     concentr
    0.26
    Generic
    0.25
    ÐľÐĺ
    0.25
    Activations Density 0.199%

    No Known Activations

    This feature has no known activations.