© 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. 25-TRANSCODER-HP
    7. 106962
    Prev
    Next
    INDEX
    Explanations

    are

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    è¿Ļæĺ¯ä¸Ģ个
    -0.35
     a
    -0.32
    ä¸Ģ个
    -0.30
    è¿Ļ个
    -0.28
    ä¸Ģ个å°ı
    -0.28
     cul
    -0.28
     this
    -0.28
    询
    -0.27
    ä¸ĢåĢĭ
    -0.27
    æľīä¸Ģ个
    -0.26
    POSITIVE LOGITS
    odings
    0.34
    ilities
    0.34
    ensions
    0.33
    okies
    0.32
     skies
    0.31
     readings
    0.30
     vibrations
    0.30
     drums
    0.30
    Ñģкие
    0.30
     gardens
    0.29
    Activations Density 1.098%

    No Known Activations