© 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. 61816
    Prev
    Next
    INDEX
    Explanations

    personal perspectives and reflections

    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
    æ°¸ä¹ħ
    -0.11
    éĶ¦
    -0.10
    åºľ
    -0.10
    绣çŃ¹
    -0.10
    ä¸
    -0.09
    ä¸įæĸŃå¢ŀ强
    -0.09
    Permanent
    -0.09
     versa
    -0.09
    åįł
    -0.08
    æī®
    -0.08
    POSITIVE LOGITS
    åĴĮ个人
    0.11
    =form
    0.10
    çļĦä¸ĢéĿ¢
    0.10
    ç¿İ
    0.09
    istic
    0.09
    æīĵæ³ķ
    0.09
     personally
    0.09
    åĴĮæĬĢæľ¯
    0.09
    åŃ¦å®¶
    0.09
     minded
    0.09
    Activations Density 0.022%

    No Known Activations