© 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. 4193
    Prev
    Next
    INDEX
    Explanations

    continue browsing

    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
    æĮŁ
    -0.09
    å·²ç»ıæľī
    -0.09
    è¿Ļæł·ä¸Ģ
    -0.08
    ìłľëıĦ
    -0.08
    å°±è¿Ļä¹Ī
    -0.08
    imir
    -0.08
    æĹłæķ°æ¬¡
    -0.08
    积èĵĦ
    -0.08
    ç¼Ł
    -0.08
    nes
    -0.08
    POSITIVE LOGITS
    继ç»Ń
    0.12
    缴åĪ°
    0.11
    ä¸ĭåİ»
    0.11
    延ç»Ń
    0.11
    缴èĩ³
    0.11
    OnError
    0.10
    åĬ¿å¤´
    0.09
     continue
    0.09
     Paramount
    0.09
     далÑĮÑĪе
    0.09
    Activations Density 0.073%

    No Known Activations