© 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. 12063
    Prev
    Next
    INDEX
    Explanations

    business entities or descriptors

    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
    åį¯
    -0.09
    å¼Ģæ°´
    -0.09
    æĮĤåľ¨
    -0.09
    CardBody
    -0.09
    åIJģ
    -0.08
    åıijè§ī
    -0.08
    tres
    -0.08
    éĿĴå²Ľå¸Ĥ
    -0.08
    çĸı
    -0.08
    秧
    -0.08
    POSITIVE LOGITS
    æģĴ
    0.10
    è¿ŀéĶģ
    0.10
    æľīéĻIJ责任
    0.09
    çļĦè®°å¿Ĩ
    0.09
    建åįİ
    0.09
    à¤Ŀ
    0.08
    åŀ£
    0.08
     Solutions
    0.08
     solutions
    0.08
    æħ
    0.08
    Activations Density 0.199%

    No Known Activations