© 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. 33641
    Prev
    Next
    INDEX
    Explanations

    list items like game stats, numbers, dates

    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
    kul
    -0.09
    诸å¦Ĥ
    -0.09
    soles
    -0.09
    OK
    -0.08
    mana
    -0.08
    çī¢
    -0.08
    åĽĽäºĶ
    -0.08
    æĢ»è£ģ
    -0.08
    noinspection
    -0.08
     sale
    -0.08
    POSITIVE LOGITS
    åĿIJ
    0.10
     umie
    0.09
    çĶ·åŃIJ
    0.09
    laus
    0.09
    enis
    0.09
    è¯ļ
    0.09
     bır
    0.08
    製
    0.08
    unist
    0.08
    å°ıèħ¿
    0.08
    Activations Density 0.007%

    No Known Activations