© 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. 32912
    Prev
    Next
    INDEX
    Explanations

    flavonoid

    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
     ме
    -0.09
    zet
    -0.09
    mer
    -0.09
    æ±Łå±±
    -0.08
    ä¸Ĭ次
    -0.08
    AspNet
    -0.08
    åĪĿ次
    -0.08
     mbox
    -0.08
    ders
    -0.08
    lse
    -0.08
    POSITIVE LOGITS
    æķķ
    0.10
    èĢģ大
    0.09
    æŃ£çīĪ
    0.09
    legg
    0.09
    éļ¼
    0.09
    æijŀ
    0.09
    æģ½
    0.08
    thal
    0.08
    è§ĨåIJ¬
    0.08
    å¯ĵæĦı
    0.08
    Activations Density 0.066%

    No Known Activations