© 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
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50906
    Prev
    Next
    INDEX
    Explanations

    flag report abuse

    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
    åıĻ
    -0.10
    æĿŁ
    -0.10
     Sized
    -0.09
    麻çĹ¹
    -0.09
    åħ±éĿĴ
    -0.09
    åİī
    -0.09
    _HARD
    -0.09
    éŨæĪ·ç½ijç«Ļ
    -0.09
    æľĢå°ij
    -0.09
    æī³
    -0.09
    POSITIVE LOGITS
    åħ¼
    0.09
    æ¤IJ
    0.09
     abuse
    0.09
    å·¥ä½ľæĬ¥åijĬ
    0.09
    ä»ĸ认为
    0.09
    è·¯éĿ¢
    0.08
    æłĩçŃ¾
    0.08
     flag
    0.08
     etiqu
    0.08
    erview
    0.08
    Activations Density 0.077%

    No Known Activations