© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 10455
    Prev
    Next
    INDEX
    Explanations

    why questions

    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
    еÑĩа
    -0.10
    ä¸İæŃ¤
    -0.09
    æĺ¯å¦Ĥä½ķ
    -0.09
    欢ä¹IJ
    -0.09
    éϤå¤ĸ
    -0.08
    å±ŀå®ŀ
    -0.08
    ä¸Ģç¬ij
    -0.08
    ä¸Ģæł·
    -0.08
    æµģæ°´
    -0.08
    åľ°æ¯¯
    -0.08
    POSITIVE LOGITS
    çļĦéĩįè¦ģæĢ§
    0.11
    çļĦ好å¤Ħ
    0.10
    éĩįè§Ĩ
    0.10
    为ä»Ģä¹Īè¦ģ
    0.10
    é«ĺ度éĩįè§Ĩ
    0.09
    好å¤Ħ
    0.09
     überhaupt
    0.09
    amac
    0.09
    ä»Ĭ
    0.09
    广大
    0.09
    Activations Density 0.074%

    No Known Activations