© 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. 27744
    Prev
    Next
    INDEX
    Explanations

    year this

    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
    zes
    -0.10
    第ä¸īæĸ¹
    -0.09
    é¾Ħ
    -0.09
    èµ·æĿ¥äºĨ
    -0.09
    éŀ
    -0.09
    åľ¨æľªæĿ¥
    -0.09
    èĩªå·±åĸľæ¬¢
    -0.09
     вÑģÑıк
    -0.09
    梳
    -0.09
    mad
    -0.09
    POSITIVE LOGITS
    ãģĬãĤĬ
    0.10
    ä¹Łä¸įä¾ĭå¤ĸ
    0.09
     emphasis
    0.09
    emphasis
    0.09
    çļĦ缮åħī
    0.08
    åħ«åŃĹ
    0.08
    tempt
    0.08
    çļĦè¯Ŀé¢ĺ
    0.08
    çļĦçľ¼åħī
    0.08
     stun
    0.08
    Activations Density 0.019%

    No Known Activations