© 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. 25605
    Prev
    Next
    INDEX
    Explanations

    other

    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
    çĶļ
    -0.28
    æľīä»·åĢ¼çļĦ
    -0.27
     Operating
    -0.27
    &q
    -0.26
    ä¸Ģç«Ļ
    -0.26
    æľīä»·åĢ¼
    -0.25
     SOUR
    -0.25
    odia
    -0.25
    æ²»
    -0.25
    names
    -0.25
    POSITIVE LOGITS
     side
    0.35
    ÑĤиÑĢов
    0.32
     sides
    0.31
    ento
    0.29
     ÑģÑĤоÑĢонÑĭ
    0.28
     sidel
    0.26
     Side
    0.26
    _SIDE
    0.25
    Side
    0.25
    mpz
    0.24
    Activations Density 0.018%

    No Known Activations