© 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. 64393
    Prev
    Next
    INDEX
    Explanations

    code 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
    Not in Any Lists

    No Comments

    Negative Logits
     Lanka
    -0.29
     caste
    -0.27
    rikes
    -0.26
     offended
    -0.26
    çıŀ
    -0.26
    æģ³
    -0.24
    casting
    -0.24
    éĢīåıĸ
    -0.24
    .toHexString
    -0.24
    æ¶Īè²»èĢħ
    -0.24
    POSITIVE LOGITS
    lip
    0.25
     sideline
    0.25
    éªł
    0.25
    println
    0.24
     spark
    0.24
     sap
    0.24
    æł·çļĦ
    0.24
     james
    0.24
    activity
    0.24
     renew
    0.24
    Activations Density 0.754%

    No Known Activations