© 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. 31905
    Prev
    Next
    INDEX
    Explanations

    core, ed, vo, dio

    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
    hel
    -0.10
    èµłéĢģ
    -0.09
    .localtime
    -0.09
    é»Ħéĩij
    -0.09
     Golf
    -0.09
     Jeg
    -0.09
    åŁĴ
    -0.08
    urette
    -0.08
    åģļå·¥
    -0.08
    éĢ¢
    -0.08
    POSITIVE LOGITS
    åı£æ°Ķ
    0.09
    çĻŀ
    0.08
    asting
    0.08
    èĬ±æł·
    0.08
    ulu
    0.08
    èļĬ
    0.08
    trak
    0.08
    æģ¶
    0.08
    å¿ĺ
    0.08
    æ¼ı
    0.08
    Activations Density 0.002%

    No Known Activations