© 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. 20-TRANSCODER-HP
    7. 106848
    Prev
    Next
    INDEX
    Explanations

    Mixed text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    iland
    -0.28
    å±IJ
    -0.28
    çļĦçIJĨæĥ³
    -0.26
    Because
    -0.25
     Because
    -0.25
    izedName
    -0.25
    deal
    -0.24
    .lib
    -0.24
    çļĦè¯Ńè¨Ģ
    -0.24
    çļĦåIJįåŃĹ
    -0.23
    POSITIVE LOGITS
    OID
    0.28
    æĸ¹éĴĪ
    0.28
    oca
    0.27
    -bel
    0.27
    itous
    0.25
    ainen
    0.24
    ']."'
    0.24
    itar
    0.24
    MEDIA
    0.24
    Ä±ÅŁÄ±
    0.24
    Activations Density 10.763%

    No Known Activations