© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 98910
    Prev
    Next
    INDEX
    Explanations

    Code/legal citations

    np_max-act · gemini-2.0-flash
    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
    æľĢéĩįè¦ģ
    -0.45
     most
    -0.41
    å°¤
    -0.37
    æľĢ主è¦ģ
    -0.35
    æĽ´éĩįè¦ģ
    -0.33
    æľĢ大çļĦ
    -0.32
    æľĢ
    -0.32
    çļĦæł¹æľ¬
    -0.31
    æľĢ为
    -0.31
    most
    -0.31
    POSITIVE LOGITS
    åı¦ä¸Ģ个
    0.35
    åı¦å¤ĸä¸Ģ个
    0.34
    ä¸ĭä¸Ģ个
    0.32
    åı¦ä¸Ģ
    0.31
    åı¦ä¸Ģç§į
    0.31
    another
    0.30
    åı¦ä¸Ģä½į
    0.30
    åı¦ä¸Ģè¾¹
    0.29
    第äºĮç§į
    0.28
    upported
    0.27
    Activations Density 0.006%

    No Known Activations