© 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. 51178
    Prev
    Next
    INDEX
    Explanations

    ask because

    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
    ä¼ļè°Ī
    -0.09
    pository
    -0.09
    porte
    -0.09
    éħ¬
    -0.09
    mandatory
    -0.09
    ä¹±
    -0.08
    _IDLE
    -0.08
    inde
    -0.08
     calming
    -0.08
    olen
    -0.08
    POSITIVE LOGITS
    æĬ±æŃī
    0.13
    ä¸į解
    0.12
    ä¸į说
    0.11
    è¿Ļä¹Ī说
    0.11
    sorry
    0.11
    æģķ
    0.10
    æĪijä¸įæĺ¯
    0.10
     ë§IJìĶĢ
    0.10
    æĤ¨çļĦåŃ©åŃIJ
    0.10
    ä¸į论
    0.10
    Activations Density 0.050%

    No Known Activations