© 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. 23532
    Prev
    Next
    INDEX
    Explanations

    asking questions and sharing information

    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
    设æĥ³
    -0.09
    åīįè¿°
    -0.08
    å¾Įä¾Ĩ
    -0.08
    URING
    -0.08
    åIJİæĿ¥
    -0.08
    åIJĦèĩªçļĦ
    -0.08
    _su
    -0.08
    åĪ¶åĵģ
    -0.08
     earlier
    -0.08
    好åĩłä¸ª
    -0.08
    POSITIVE LOGITS
    иж
    0.11
    è¿Ļæł·ä¸Ģ个
    0.11
    è¿ĻèĪ¬
    0.10
    è¿Ļä¹Īå¤ļ
    0.10
    éĻĮçĶŁ
    0.10
    ç»Īäºİ
    0.10
    èĩªèIJ¥
    0.10
    å¤ļä¹Ī
    0.10
    è¿Ļä¸ĢåĪ»
    0.10
    çī¹æ®ĬçļĦ
    0.09
    Activations Density 0.178%

    No Known Activations