© 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. 5884
    Prev
    Next
    INDEX
    Explanations

    cooking

    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
     acre
    -0.10
    unken
    -0.09
    aisy
    -0.08
     Senior
    -0.08
    饼干
    -0.08
    openh
    -0.08
    asper
    -0.08
    åѤç«ĭ
    -0.08
     libr
    -0.08
    ä½Ķ
    -0.08
    POSITIVE LOGITS
    è¢ħ
    0.09
    娣
    0.09
     barbecue
    0.09
     Holder
    0.09
    çĤİ
    0.09
    海滨
    0.09
    çĥ§çĥ¤
    0.09
    Leaks
    0.08
    éļıæīĭ
    0.08
    Bracket
    0.08
    Activations Density 0.033%

    No Known Activations