© 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. 111513
    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
     MAC
    -0.25
     AAC
    -0.25
    isc
    -0.25
     Mac
    -0.25
     MSC
    -0.24
     #-}↵↵
    -0.24
     ÐļÑĢоме
    -0.24
    (mac
    -0.23
    iosk
    -0.23
     Trim
    -0.23
    POSITIVE LOGITS
    INGLE
    0.28
    åĽ½åĬ¡
    0.26
    ä¸Ńè¶ħ
    0.26
    æĪij羣çļĦ
    0.24
    yat
    0.24
    éĩįè¦ģ
    0.24
    以ä¸ĬçļĦ
    0.24
    SUPER
    0.24
     outweigh
    0.24
    urat
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.