© 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. 12-TRANSCODER-HP
    7. 22028
    Prev
    Next
    INDEX
    Explanations

    Machinery, patents, and manuals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æ®ĸ
    -0.26
    è·ĥ
    -0.26
    æ®ĭå¿į
    -0.25
    ä¸Ģå¼Ģå§ĭå°±
    -0.25
    ifice
    -0.24
    irst
    -0.24
    achten
    -0.24
     Presidency
    -0.24
    azen
    -0.24
    uate
    -0.24
    POSITIVE LOGITS
    addir
    0.27
    dì
    0.26
    çªĿ
    0.26
    /documentation
    0.26
     ÑģÑĦ
    0.26
     Lö
    0.26
     Äijò
    0.26
    ionario
    0.26
     quarter
    0.25
    >{@
    0.25
    Activations Density 0.008%

    No Known Activations