© 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. 99226
    Prev
    Next
    INDEX
    Explanations

    same or equal

    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
     switch
    -0.33
    switch
    -0.29
     Switch
    -0.28
    åĪĩæį¢
    -0.27
    anoi
    -0.27
    Switch
    -0.27
     switching
    -0.26
     switches
    -0.26
     amounted
    -0.25
    çĻ»éĻĨ
    -0.25
    POSITIVE LOGITS
    æ¯Ķä¾ĭ
    0.76
     proportion
    0.68
    çļĦæ¯Ķä¾ĭ
    0.66
     ratios
    0.65
     proportions
    0.62
     proportional
    0.57
     ratio
    0.56
    ratio
    0.52
    Ratio
    0.52
     Ratio
    0.48
    Activations Density 0.001%

    No Known Activations