© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36986
    Prev
    Next
    INDEX
    Explanations

    varieties, cultivars, breeds, strains

    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
    åĶ§
    -0.09
    ä¸įèĪĴæľį
    -0.09
    æī©å¤§
    -0.09
    åĬłæ²¹
    -0.09
    积
    -0.09
    chy
    -0.09
    ç©į
    -0.09
    UGC
    -0.09
    æ»ļæ»ļ
    -0.09
     Planet
    -0.09
    POSITIVE LOGITS
    åĵģç§į
    0.19
    æĶ¹èī¯
    0.14
     varieties
    0.14
    磮
    0.13
    ç§įæ¤į
    0.12
     strains
    0.12
     breeds
    0.11
    æłª
    0.10
    æľºåŀĭ
    0.10
    åŁ¹èĤ²
    0.10
    Activations Density 0.240%

    No Known Activations