© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 1984
    Prev
    Next
    INDEX
    Explanations

    bike shops and reviews

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aires
    -0.12
    ãģĦãĤĭ
    -0.12
    aries
    -0.11
    ateur
    -0.11
    ator
    -0.11
    ible
    -0.10
    ance
    -0.10
    ixed
    -0.10
    istance
    -0.09
    ively
    -0.09
    POSITIVE LOGITS
    ernet
    0.10
    lets
    0.10
    ographed
    0.10
    ä¸ĭ乡
    0.09
    /library
    0.09
     vá»±c
    0.09
    laus
    0.09
    let
    0.08
    ม
    0.08
    heimer
    0.08
    Activations Density 0.006%

    No Known Activations