© 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. 6574
    Prev
    Next
    INDEX
    Explanations

    Chinese medicine, function, death, sour taste

    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
    iar
    -0.10
    adro
    -0.10
    æijĺ
    -0.09
    é¹Ń
    -0.09
    çĵ
    -0.08
    èı¡
    -0.08
    åīĥ
    -0.08
    çĭ®åŃIJ
    -0.08
    kers
    -0.08
    uParam
    -0.08
    POSITIVE LOGITS
    äºĶè¡Į
    0.12
    ä¸ĢåĪĨ
    0.10
    æ³»
    0.09
    æijĦ
    0.09
    æĺ¥å¤ı
    0.09
    èĦ¾èĥĥ
    0.09
    èĤłèĥĥ
    0.09
    èī®
    0.09
    åħ«åį¦
    0.09
    çĶŁæ°Ķ
    0.09
    Activations Density 0.016%

    No Known Activations