© 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. 33092
    Prev
    Next
    INDEX
    Explanations

    theme or templates

    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
    çĤĴèĤ¡
    -0.09
    èİł
    -0.08
    å·¡æŁ¥
    -0.08
    çħ®
    -0.08
     Ages
    -0.08
    æ¹Ł
    -0.08
    leigh
    -0.08
    orage
    -0.08
    .Compile
    -0.08
    åŁĭ
    -0.08
    POSITIVE LOGITS
    模æĿ¿
    0.12
     Theme
    0.10
    衬
    0.09
    西è£ħ
    0.09
     templates
    0.09
     theme
    0.09
    Theme
    0.09
    -built
    0.09
    æ³ĵ
    0.09
     THEME
    0.09
    Activations Density 0.208%

    No Known Activations