© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38351
    Prev
    Next
    INDEX
    Explanations

    asking questions, receiving gifts, defeat, money

    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
    æĦīå¿«
    -0.08
    okus
    -0.08
     Bh
    -0.08
    ritch
    -0.08
    ä¸įå®ī
    -0.08
    éļIJ
    -0.07
    å½ĵ天
    -0.07
    kus
    -0.07
     Rag
    -0.07
    åįļ
    -0.07
    POSITIVE LOGITS
    ä½łèĩªå·±
    0.12
    éĹ®æĪij
    0.12
    æĪijèĩªå·±
    0.12
     ìĦľë¡ľ
    0.11
    ä»ĸèĩªå·±
    0.11
    éŁ¿
    0.11
    被æī§è¡Į
    0.11
    被人
    0.11
    å½ĸ
    0.10
    AGR
    0.10
    Activations Density 1.364%

    No Known Activations