© 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. 34446
    Prev
    Next
    INDEX
    Explanations

    games against

    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
    åĪĿ次
    -0.09
    .addAll
    -0.09
    åĬŁå¤«
    -0.09
    wald
    -0.09
    vit
    -0.08
    æĪ¿éĹ´
    -0.08
    åģļäºĭ
    -0.08
    åĨľä½ľçī©
    -0.08
    è¿Ļ次
    -0.08
    è¹²
    -0.08
    POSITIVE LOGITS
    ç»ĵæĿŁåIJİ
    0.10
    aky
    0.10
    ILI
    0.09
     ÑģÑĢедÑģÑĤв
    0.09
    款
    0.09
    ACHI
    0.09
    声åĵį
    0.09
    endi
    0.09
    aho
    0.09
    ç²¾ç¥ŀæĸĩæĺİ
    0.08
    Activations Density 0.026%

    No Known Activations