© 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. 5099
    Prev
    Next
    INDEX
    Explanations

    select correct or incorrect

    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
     exp
    -0.08
    /exp
    -0.08
    çŃīå¾ħ
    -0.08
    éĢı
    -0.08
    æŀķ头
    -0.08
    пон
    -0.08
    reek
    -0.08
     nick
    -0.07
    è·¨çķĮ
    -0.07
    æĺµ
    -0.07
    POSITIVE LOGITS
    çĤľ
    0.09
    å½ĵæĪIJ
    0.09
    æIJŃéħį
    0.09
    å±ŀäºİèĩªå·±
    0.09
    æł¸æŁ¥
    0.09
    æŃ£ãģĹãģĦ
    0.09
    ró
    0.09
    åľ¨çĶŁæ´»ä¸Ń
    0.09
     дол
    0.09
    æŶæĬ¥
    0.09
    Activations Density 0.119%

    No Known Activations