© 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. 27706
    Prev
    Next
    INDEX
    Explanations

    links after closing bracket

    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
    à¹Ģย
    -0.09
    ä¹ŀ
    -0.08
    olum
    -0.08
    ãģ»ãģĨ
    -0.08
    OrNil
    -0.08
    æ·³
    -0.08
    _REPLY
    -0.08
    讨
    -0.08
    祥
    -0.08
    åIJij社ä¼ļ
    -0.08
    POSITIVE LOGITS
    è¿Ļæł·çļĦè¯Ŀ
    0.10
    åIJĪä½ľä¼Ļä¼´
    0.10
    æĪĺçķ¥åIJĪä½ľ
    0.10
    å¹³åı°
    0.09
    é©´
    0.09
    æĹĹä¸ĭçļĦ
    0.09
    åIJĪä½ľåħ³ç³»
    0.09
    æĬ¼
    0.09
    符
    0.09
    ç³Ĭæ¶Ĥ
    0.09
    Activations Density 0.004%

    No Known Activations