© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9514
    Prev
    Next
    INDEX
    Explanations

    guidelines

    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
    ivate
    -0.12
    æł·åŃIJ
    -0.11
    деÑģÑıÑĤ
    -0.10
    ful
    -0.10
    æĸ¹ä¾¿
    -0.09
    ooth
    -0.09
    ilation
    -0.09
    enal
    -0.09
    itive
    -0.09
    å¤©çľŁ
    -0.09
    POSITIVE LOGITS
    ìĤ¬íķŃ
    0.12
    arity
    0.09
    coc
    0.09
    ãģĹãģ¾ãģĨ
    0.08
    å°ijæķ°
    0.08
    à¸ĩ
    0.08
    åŁºæľ¬åİŁåĪĻ
    0.08
    ол
    0.08
    åİŁåīĩ
    0.08
    áĥŀ
    0.08
    Activations Density 0.009%

    No Known Activations