© 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. 18093
    Prev
    Next
    INDEX
    Explanations

    linguistic terms and expressions

    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
    eced
    -0.09
    å·¥ä½ľæľºåĪ¶
    -0.08
    婪
    -0.08
     Dest
    -0.08
    æ¡ĤèĬ±
    -0.08
     Passage
    -0.08
    ä½įåĪĹ
    -0.08
    该项
    -0.08
    åĶ±
    -0.08
    è¹ļ
    -0.08
    POSITIVE LOGITS
    è¯į
    0.11
    常çĶ¨
    0.10
    è¾ŀ
    0.10
    åĥ»
    0.09
    è¯įæ±ĩ
    0.09
    纪
    0.09
    è©ŀ
    0.09
    scal
    0.09
    ä¿ļ
    0.09
    _unc
    0.09
    Activations Density 0.114%

    No Known Activations