© 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. 55672
    Prev
    Next
    INDEX
    Explanations

    research and investigation

    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
    æĹĥ
    -0.10
    æīĥ
    -0.09
    æķĻèĤ²åŁ¹è®Ń
    -0.09
    ç¾²
    -0.09
    ä¸ľè·¯
    -0.09
    åĵ²
    -0.09
    ÑĪиб
    -0.09
    _tpl
    -0.08
    çķı
    -0.08
    è¯ī
    -0.08
    POSITIVE LOGITS
    æŁ¥éĺħ
    0.18
    æŁ¥æī¾
    0.16
    æIJľç´¢
    0.13
    調ãģ¹
    0.13
    èµĦæĸĻ
    0.13
    åľ¨ç½ijä¸Ĭ
    0.13
    æŁ¥è¯¢
    0.12
    ä¸Ĭç½ij
    0.12
    èµĦæĸĻæĺ¾ç¤º
    0.12
    æŁ¥
    0.12
    Activations Density 0.175%

    No Known Activations