© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7732
    Prev
    Next
    INDEX
    Explanations

    said to be

    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
    äºĨèĩªå·±çļĦ
    -0.09
    èģĶç½ij
    -0.09
    çľĭä½ł
    -0.09
    ROY
    -0.09
    åĵŃäºĨ
    -0.08
    举åįĹ
    -0.08
    ä¹īä¹Į
    -0.08
    å¾Ģå¾Ģä¼ļ
    -0.07
    kar
    -0.07
    uber
    -0.07
    POSITIVE LOGITS
    zelf
    0.13
    éĩįå·¥
    0.10
    åľ¨æ¸¸æĪıä¸Ń
    0.10
    apult
    0.10
    åīįæıIJæĺ¯
    0.09
    ness
    0.09
    uels
    0.09
    monton
    0.09
    iful
    0.09
    cape
    0.09
    Activations Density 0.018%

    No Known Activations