© 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. 33987
    Prev
    Next
    INDEX
    Explanations

    says or believes

    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
    odal
    -0.10
    æĪijè¿ĺæĺ¯
    -0.10
    è¿Ļæīį
    -0.09
    好äºĭ
    -0.09
    çŁ¥éģĵäºĨ
    -0.09
    èĮĥ
    -0.09
    è¿Ļä¹Ł
    -0.09
    sortBy
    -0.09
    èijĨ
    -0.09
     blobs
    -0.08
    POSITIVE LOGITS
    æĺ¯æľĢ
    0.10
    Ĥæķ°
    0.09
    æĺ¯åľ¨
    0.09
    æĺ¯ä¸Ģ
    0.08
    ledge
    0.08
    å·²ç»ı
    0.08
     repr
    0.08
     Dit
    0.08
    å¤Ħåľ¨
    0.08
    æĺ¯ä¸ºäºĨ
    0.08
    Activations Density 0.034%

    No Known Activations