© 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. 7461
    Prev
    Next
    INDEX
    Explanations

    strictly or purely

    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
    åīįæīĢ
    -0.09
     Vad
    -0.09
    åįĬæľĪ
    -0.09
    ÙĬØ¡
    -0.08
    aku
    -0.08
    æł¹æľ¬æ²¡æľī
    -0.08
    è´¨éĩıå®īåħ¨
    -0.08
    aga
    -0.08
    æľī人说
    -0.08
    è¾ĩ
    -0.08
    POSITIVE LOGITS
    纯
    0.12
    åĩŃ
    0.11
    ç²¹
    0.11
    纯粹
    0.11
     purely
    0.11
    ä¾ĿéĿł
    0.11
    ä¸įéĢļ
    0.10
    éĿł
    0.10
     pure
    0.10
    ç´Ķ
    0.10
    Activations Density 0.019%

    No Known Activations