© 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. 25491
    Prev
    Next
    INDEX
    Explanations

    know

    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
    éĩį
    -0.28
    é¢Ľ
    -0.27
    æĹłéľĢ
    -0.25
    здание
    -0.24
    visor
    -0.24
    AtA
    -0.24
    ãĤ¤ãĥĪ
    -0.24
    odash
    -0.24
    ä¸Ģ对ä¸Ģ
    -0.23
    UBLE
    -0.23
    POSITIVE LOGITS
    çļĦ人æĿ¥è¯´
    0.29
    åħļæĶ¿
    0.27
    ore
    0.26
    åĿŀ
    0.26
    oplan
    0.26
    iland
    0.26
     [].
    0.25
    utron
    0.25
    ORE
    0.25
    æĪijè®°å¾Ĺ
    0.24
    Activations Density 0.061%

    No Known Activations