© 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. 57097
    Prev
    Next
    INDEX
    Explanations

    Michelin star, future results

    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
    rant
    -0.10
    aries
    -0.10
    RICT
    -0.10
    -spacing
    -0.09
    æĻ®
    -0.09
    åīª
    -0.08
    inia
    -0.08
    MORE
    -0.08
    NONE
    -0.08
    isc
    -0.08
    POSITIVE LOGITS
    athom
    0.11
    æºı
    0.10
    è·¨çķĮ
    0.09
    vla
    0.09
    ä¸ļ
    0.09
    èĥĸåŃIJ
    0.09
    壮
    0.08
    çģ°
    0.08
    壯
    0.08
    绳
    0.08
    Activations Density 0.002%

    No Known Activations