© 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. 37459
    Prev
    Next
    INDEX
    Explanations

    in a manner

    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
    åĩºçīĪ
    -0.09
    åĵŃæ³£
    -0.09
    ensi
    -0.08
    æĬĺèħ¾
    -0.08
    Active
    -0.08
    rale
    -0.08
    ÑĢог
    -0.08
    åķ¸
    -0.08
    éĻ·éĺ±
    -0.08
    æıª
    -0.08
    POSITIVE LOGITS
     manner
    0.21
     manners
    0.14
     fashion
    0.12
    æĸ¹å¼ıè¿Ľè¡Į
    0.10
    æĸ¹å¼ı
    0.10
    çļĦæĸ¹å¼ı
    0.10
    æ°ijæĦı
    0.10
    anner
    0.09
     manière
    0.09
    çĬ¶
    0.09
    Activations Density 0.070%

    No Known Activations