© 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. 17794
    Prev
    Next
    INDEX
    Explanations

    analytic description and models

    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
    orate
    -0.08
    IRO
    -0.08
    ajo
    -0.08
    quo
    -0.08
    pron
    -0.08
    ä¹¾åĿ¤
    -0.08
    ç¿ĺ
    -0.08
    engl
    -0.08
    ktop
    -0.07
    ivot
    -0.07
    POSITIVE LOGITS
    模åŀĭ
    0.16
    ãĥ¢ãĥĩãĥ«
    0.16
     models
    0.15
     model
    0.12
    æııè¿°
    0.12
     моделÑĮ
    0.12
     Models
    0.12
    åħ¬å¼ı
    0.11
    models
    0.11
     модели
    0.11
    Activations Density 0.477%

    No Known Activations