© 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. 58893
    Prev
    Next
    INDEX
    Explanations

    curcumin and spices

    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
    奸
    -0.10
    ettes
    -0.09
    å®ļäºĨ
    -0.09
    æĬĬèĩªå·±
    -0.09
     Wäh
    -0.09
    elligence
    -0.09
    layan
    -0.09
    spath
    -0.09
     alas
    -0.08
    eway
    -0.08
    POSITIVE LOGITS
    ä¸įèĪį
    0.09
    é¼ĵ
    0.08
     fas
    0.08
    @c
    0.08
    å¿ĥåĬ¨
    0.08
     Churchill
    0.08
    ä¼ł
    0.07
    èµıæŀIJ
    0.07
     pow
    0.07
    åľ¨åħ¨çIJĥ
    0.07
    Activations Density 0.005%

    No Known Activations