© 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. 88760
    Prev
    Next
    INDEX
    Explanations

    Need, requirement, justification

    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
    Negative Logits
    Wars
    -0.26
    kke
    -0.25
    èij¡èIJĦçīĻ
    -0.25
    æ±ģ
    -0.25
    hair
    -0.25
    pw
    -0.24
    jam
    -0.24
     Weld
    -0.23
    å§Ķä¼ļ
    -0.23
     Cheap
    -0.23
    POSITIVE LOGITS
    aneously
    0.28
    æĽ´è¦ģ
    0.27
    ä¹İ
    0.27
    è¦ģçĶ¨
    0.26
    @stop
    0.25
    åł¡
    0.25
    ä¸įåģļ
    0.25
     gio
    0.25
    {return
    0.25
    ulin
    0.24
    Activations Density 0.007%

    No Known Activations