© 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. 23-TRANSCODER-HP
    7. 23530
    Prev
    Next
    INDEX
    Explanations

    Compatibility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    èĿĩ
    -0.28
     amet
    -0.26
    atee
    -0.26
    yms
    -0.25
    ÃŃd
    -0.25
    åĪijäºĭæ¡Ī件
    -0.25
    AndWait
    -0.24
     dsp
    -0.24
    eree
    -0.24
     rf
    -0.23
    POSITIVE LOGITS
    æĢ§
    0.32
    æĢ§å¼º
    0.31
    nano
    0.31
    æĢ§çļĦ
    0.29
    tau
    0.29
    .PI
    0.27
    ×ŀק
    0.26
    ëĿ¼ëıĦ
    0.26
    èIJİ
    0.26
     quali
    0.25
    Activations Density 0.124%

    No Known Activations