© 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. 1298
    Prev
    Next
    INDEX
    Explanations

    guessing or suspicion

    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
    æķ°æį®æĺ¾ç¤º
    -0.09
    è¿ĺ好
    -0.09
    æīįçŁ¥éģĵ
    -0.09
    ç«Ł
    -0.09
    ä¸ĢåIJį
    -0.09
    ä¹Łè®¸
    -0.09
    PEND
    -0.08
    å±ħçĦ¶
    -0.08
    .fn
    -0.08
    羣åĪĩ
    -0.08
    POSITIVE LOGITS
    ãģ®ãģĵãģ¨
    0.10
    çħ½
    0.09
    åıijæĮ¥äºĨ
    0.09
    è¿Ļåľºæ¯ĶèµĽ
    0.09
    éľĩ
    0.09
    ulin
    0.09
    æIJĵ
    0.09
     headed
    0.09
    ÑĢаб
    0.09
    è¿Ļéĥ¨
    0.08
    Activations Density 0.043%

    No Known Activations