© 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. 54301
    Prev
    Next
    INDEX
    Explanations

    it is (essential/crucial/important) that

    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
    æģIJ
    -0.11
    å¾Īåı¯èĥ½
    -0.10
    å¾Īæľīåı¯èĥ½
    -0.10
    åı¯èĥ½æĢ§
    -0.09
    ãģįãģ£ãģ¨
    -0.09
     ÑģамÑĭм
    -0.08
    åı¯èĥ½æĺ¯
    -0.08
    ä¸Ģåı¥
    -0.08
    æĸ¹æīį
    -0.08
    finity
    -0.08
    POSITIVE LOGITS
    å°½æĹ©
    0.12
    认è¯ĨåĪ°
    0.11
    尽快
    0.11
     accurate
    0.10
    åĩĨç¡®
    0.10
    æľīè¶³å¤ŁçļĦ
    0.10
    ä¹Łåıªèĥ½
    0.10
    åIJĥåĪ°
    0.10
    æĺİçĻ½
    0.09
    æľīä¸Ģå®ļçļĦ
    0.09
    Activations Density 0.039%

    No Known Activations