© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50741
    Prev
    Next
    INDEX
    Explanations

    probability calculations

    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
    iente
    -0.09
    失踪
    -0.09
    ç»Ļèĩªå·±
    -0.09
    itis
    -0.08
    çĨ
    -0.08
    -like
    -0.08
     życ
    -0.08
    èĬ±å¼Ģ
    -0.08
    -phase
    -0.08
    ovsky
    -0.08
    POSITIVE LOGITS
    æĪijå¾Ī
    0.08
    ãģ¯ãĤĤãģ¡ãĤįãĤĵ
    0.08
    æ¡Ĥ
    0.08
    icho
    0.08
    ÑĢÑĥÑĤ
    0.08
    éĻĪè¿°
    0.08
    MainThread
    0.07
    çļĦåIJĦ项
    0.07
    .layout
    0.07
    çļĦè§Ĵ度
    0.07
    Activations Density 0.563%

    No Known Activations