© 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. 111478
    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
    åĢŁåı£
    -0.27
    å¥ģ
    -0.26
    åŀ®
    -0.25
    cloak
    -0.24
    ç»Ŀ
    -0.23
    çļĦè¦ģæ±Ĥ
    -0.23
     pretext
    -0.23
     strapped
    -0.23
    æŶå°ļ
    -0.23
    åīįæıIJæĺ¯
    -0.23
    POSITIVE LOGITS
    ibile
    0.27
    عة
    0.25
     Shadow
    0.24
    ARN
    0.24
     Stand
    0.23
    endir
    0.23
    **(
    0.23
    ä¸ĭãģĴ
    0.22
    _ENCODING
    0.22
    ifle
    0.22
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.