© 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. 64888
    Prev
    Next
    INDEX
    Explanations

    0

    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
     Marble
    -0.24
    åī©ä¸ĭ
    -0.24
     longitud
    -0.24
     rele
    -0.24
    ignal
    -0.24
    urette
    -0.23
     signalling
    -0.23
    uestas
    -0.23
     testcase
    -0.23
    UPPORT
    -0.23
    POSITIVE LOGITS
    ipped
    0.32
    idar
    0.25
    å¸ij
    0.24
    lated
    0.24
    inning
    0.24
    åħ³éŨ
    0.24
     onHide
    0.23
    第äºĮç§į
    0.23
    ói
    0.23
     among
    0.23
    Activations Density 0.395%

    No Known Activations