© 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. 48246
    Prev
    Next
    INDEX
    Explanations

    Gibson, Crawford, SON

    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
    busters
    -0.09
    íį¼
    -0.09
    åĴĮ个人
    -0.09
    æĸ°å½¢åĬ¿ä¸ĭ
    -0.09
    ific
    -0.09
    enever
    -0.09
    ç©°
    -0.09
    ena
    -0.09
    ä¼łçľŁ
    -0.09
    åķ¡
    -0.08
    POSITIVE LOGITS
    adal
    0.10
    gle
    0.09
    åı±
    0.09
    lox
    0.09
    Ñĥл
    0.08
     vice
    0.08
    ÐĿÐķ
    0.08
    亮丽
    0.08
    ed
    0.08
    uting
    0.08
    Activations Density 0.005%

    No Known Activations