© 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. 38977
    Prev
    Next
    INDEX
    Explanations

    become

    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
    åĪĿ次
    -0.12
    å½ĵåį³
    -0.10
    æ¶ī
    -0.09
    ç«ĭåį³
    -0.09
    è´Łè´£ä»»
    -0.09
    èĤ¯å®ļ
    -0.09
    IONS
    -0.09
    éĩijéĻµ
    -0.09
     Immediately
    -0.09
     ÑģÑĢазÑĥ
    -0.09
    POSITIVE LOGITS
    æĪIJ为äºĨ
    0.19
    åıĺå¾Ĺ
    0.19
     become
    0.19
    æĪIJäºĨ
    0.18
    æĪIJ为
    0.18
    æĪIJ为ä¸ŃåĽ½
    0.18
    åıĺæĪIJ
    0.18
    à¸ģลาย
    0.17
    åıĺæĪIJäºĨ
    0.17
    å·²æĪIJ为
    0.17
    Activations Density 0.132%

    No Known Activations