© 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. 17085
    Prev
    Next
    INDEX
    Explanations

    **macrocephaly**, **academic software**, **beer**, **polymeric**, **clam-shell**

    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
    иде
    -0.08
    çł·
    -0.08
    LABEL
    -0.08
    èģĮåĬ¡
    -0.08
    èī®
    -0.07
    å¼Ľ
    -0.07
    大å®Ĺ
    -0.07
    çķı
    -0.07
    è¥Ł
    -0.07
    quarter
    -0.07
    POSITIVE LOGITS
    鲤
    0.11
    åĻĻ
    0.10
    ollen
    0.09
    åĪ·
    0.09
    ssi
    0.09
    溢
    0.09
    ä¼ģä¸ļæıIJä¾Ľ
    0.09
    è·Į
    0.08
     SimpleName
    0.08
    å®Ŀå¦Ī
    0.08
    Activations Density 0.573%

    No Known Activations