© 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. 38830
    Prev
    Next
    INDEX
    Explanations

    of a

    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
    icorn
    -0.10
    容è²Į
    -0.10
    è¿Ļäºĭ
    -0.10
    é¢ľåĢ¼
    -0.10
    åīįæıIJæĺ¯
    -0.10
    çļĦè¦ģæ±Ĥ
    -0.09
    çļĦ身影
    -0.09
    åĬĽæ±Ĥ
    -0.09
     ÑģиÑĤÑĥаÑĨиÑı
    -0.09
    çľ¼çļ®
    -0.09
    POSITIVE LOGITS
    erras
    0.09
    åĨįéĢł
    0.09
     utmost
    0.08
    ndon
    0.08
    çݰ代
    0.08
     zro
    0.08
     못
    0.07
    çŁ¥éģĵäºĨ
    0.07
     modern
    0.07
    ost
    0.07
    Activations Density 0.090%

    No Known Activations