© 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. 53334
    Prev
    Next
    INDEX
    Explanations

    in favor of

    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
    hip
    -0.09
    æĮĩçĤ¹
    -0.09
    å·¾
    -0.08
     reel
    -0.08
    inged
    -0.08
     des
    -0.08
    æ¸ħæ¥ļ
    -0.08
    çļĦæķĻåѦ
    -0.08
    å¾Īæ¸ħæ¥ļ
    -0.08
    å®ĩ
    -0.07
    POSITIVE LOGITS
    éĻ¤éĿŀ
    0.11
    çľĭå¾ħ
    0.11
    å°½éĩı
    0.11
    åĵªæĢķ
    0.11
    æľĢ大ç¨ĭ度
    0.10
    ä¿¡çĶ¨
    0.10
    å°½åı¯èĥ½
    0.10
    æºIJ头
    0.10
    èĴĮ
    0.09
    æĤ²è§Ĥ
    0.09
    Activations Density 0.047%

    No Known Activations