© 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. 53721
    Prev
    Next
    INDEX
    Explanations

    scores and runs

    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
    IFE
    -0.10
    许
    -0.10
    ä¸ĩ个
    -0.10
    opi
    -0.09
    avery
    -0.09
     tiên
    -0.09
    å½ĵéĢī
    -0.09
    æĪijä¸įæĺ¯
    -0.09
    éļIJ
    -0.09
     hybrids
    -0.09
    POSITIVE LOGITS
    çŁŃæŶéĹ´åĨħ
    0.10
    è¿ħéĢŁ
    0.10
    รวà¸Ķ
    0.10
    ä¸Ģä¸ĭåŃIJå°±
    0.09
    rapid
    0.09
    ä¸Ģä¸ĭåŃIJ
    0.09
    è¿ħ
    0.09
    PGA
    0.09
    HttpResponse
    0.08
    ç«Ł
    0.08
    Activations Density 0.022%

    No Known Activations