© 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. 2269
    Prev
    Next
    INDEX
    Explanations

    even

    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
    ä¹ŁæŃ£æĺ¯
    -0.12
    ä¹Łå¾Ī
    -0.11
    ãģ¡ãĤĩãģĨãģ©
    -0.11
    æĪij羣çļĦ
    -0.11
    æŃ£å¥½
    -0.10
    羣çļĦå¾Ī
    -0.10
    ä¹Łä¸įéĶĻ
    -0.10
    åıĪä¸Ģ次
    -0.10
    æĪijåıĪ
    -0.10
    ä¹Łå°±
    -0.09
    POSITIVE LOGITS
    ä¾ĭå¤ĸ
    0.14
    æľīæŶåĢĻ
    0.10
    оÑĢо
    0.09
     ë¶Ī구íķĺê³ł
    0.09
    å¾Ĺèµ·
    0.09
    asco
    0.09
    ANGO
    0.09
    exceptions
    0.09
    ваÑĢ
    0.09
     иногда
    0.08
    Activations Density 0.082%

    No Known Activations