© 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. 6583
    Prev
    Next
    INDEX
    Explanations

    should, that's, it's, as

    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
    æĵİ
    -0.10
    à¹Īà¸Ńย
    -0.08
    æ¯ķç«Ł
    -0.08
    hetto
    -0.08
    åĥıæĺ¯
    -0.08
    çµ²
    -0.08
     przecież
    -0.08
    å°¤åħ¶æĺ¯åľ¨
    -0.08
    ä¸ŃéĹ´
    -0.08
    æķ°æį®æĺ¾ç¤º
    -0.08
    POSITIVE LOGITS
    å®ĮäºĨ
    0.12
    大èĩ´
    0.12
    说å®Į
    0.11
    ä¸įå¤ļ
    0.10
    å§Ķå±Ī
    0.10
    åŁºæľ¬æĥħåĨµ
    0.10
    å°±è¿Ļæł·
    0.09
    å®Įæ¯ķ
    0.09
    å®Į
    0.09
    à¸Ħรà¸ļ
    0.09
    Activations Density 0.017%

    No Known Activations