© 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. 52429
    Prev
    Next
    INDEX
    Explanations

    definition verb

    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
    è±ĨèħIJ
    -0.08
    åıªæĺ¯ä¸ºäºĨ
    -0.08
    å°±è¯Ĭ
    -0.08
    è¶Ĭ
    -0.08
    åIJįå½ķ
    -0.08
    sr
    -0.08
    表åĨ³
    -0.08
     kino
    -0.08
    èĨĺ
    -0.08
    çŃĶçĸij
    -0.07
    POSITIVE LOGITS
    è°ĵ
    0.11
    ODO
    0.10
    è¬Ĥ
    0.10
    形容
    0.09
    çĸ
    0.09
    ç»ĻåŃ©åŃIJ
    0.09
    è¾Ĺ
    0.09
    æŧ
    0.09
    æ¯Ķåĸ»
    0.09
    è¿Ļ个人
    0.08
    Activations Density 0.083%

    No Known Activations