© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38289
    Prev
    Next
    INDEX
    Explanations

    ACC conference and sports

    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
    ä¸Ģä¸Ģ
    -0.09
    ç¥ŀç§ĺ
    -0.09
    scape
    -0.09
    apture
    -0.08
    ner
    -0.08
     nháºŃt
    -0.08
     hitch
    -0.08
    èĥª
    -0.08
    دÙĪ
    -0.08
    upt
    -0.08
    POSITIVE LOGITS
    æĸ¯åĿ¦
    0.09
    èĴº
    0.08
    æīĭå¥Ĺ
    0.08
    åľ°åĮºçļĦ
    0.08
    .Features
    0.08
    ä¸į足
    0.08
    elan
    0.08
     Dead
    0.08
    oney
    0.08
    aines
    0.08
    Activations Density 0.004%

    No Known Activations