© 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. 142309
    Prev
    Next
    INDEX
    Explanations

    code manipulation

    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
     congr
    -0.29
    é¦Ĩ
    -0.28
    дол
    -0.27
    adar
    -0.26
    å½ĵä¸ĭ
    -0.25
    ihil
    -0.24
    cura
    -0.24
    burgh
    -0.24
    ADED
    -0.24
    agram
    -0.24
    POSITIVE LOGITS
    æľĢ好çļĦ
    0.27
     pinch
    0.26
    ä¸įåĩº
    0.24
    are
    0.24
    reak
    0.24
     tỼi
    0.24
    æĿ¥çļĦ
    0.23
    éĹ°
    0.23
    nest
    0.22
    .KeyEvent
    0.22
    Activations Density 4.217%

    No Known Activations