© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 130773
    Prev
    Next
    INDEX
    Explanations

    single digits

    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
    Not in Any Lists

    No Comments

    Negative Logits
     thereof
    -0.27
     carrying
    -0.26
    å°Ĩèĩªå·±çļĦ
    -0.26
    обоÑĢоÑĤ
    -0.26
    pac
    -0.26
    èIJ½
    -0.25
    ing
    -0.25
    äºİ
    -0.25
     rounds
    -0.24
     silver
    -0.24
    POSITIVE LOGITS
    ucha
    0.30
    reeze
    0.29
     mó
    0.28
     INTERFACE
    0.27
     actu
    0.26
    gráfico
    0.26
    iline
    0.26
    strup
    0.26
    afi
    0.25
    RunLoop
    0.25
    Activations Density 0.540%

    No Known Activations