© 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. 63941
    Prev
    Next
    INDEX
    Explanations

    xml and food

    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
    gest
    -0.29
    aturing
    -0.28
     negatives
    -0.28
    ester
    -0.26
    è·³èĪŀ
    -0.26
    ç¼Ķ
    -0.26
    CERT
    -0.24
     pé
    -0.23
    atial
    -0.23
    RAY
    -0.23
    POSITIVE LOGITS
     Dra
    0.27
    éĴİ
    0.27
    累累
    0.24
    пиÑģÑĭва
    0.24
    ylvania
    0.24
    zeigen
    0.24
    软
    0.23
     arch
    0.23
     Shields
    0.23
    brush
    0.23
    Activations Density 3.938%

    No Known Activations