© 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. 63244
    Prev
    Next
    INDEX
    Explanations

    good condition or agreement

    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
    anus
    -0.09
    eus
    -0.08
    inous
    -0.08
    ì¿ł
    -0.08
    æļĤç¼ĵ
    -0.08
    åĨį
    -0.08
    å¼±
    -0.08
     unanim
    -0.08
    æ§Ń
    -0.08
    ä¸ĵçıŃ
    -0.08
    POSITIVE LOGITS
    éķ¿èĢģ
    0.09
    åģ¶åĥı
    0.09
    å¹½é»ĺ
    0.09
    edBy
    0.09
    .fixture
    0.09
    ä»¥äººä¸ºæľ¬
    0.08
    æ¦ľ
    0.08
    大åİħ
    0.08
    ä¸ĩæĪ·
    0.08
     hog
    0.08
    Activations Density 0.009%

    No Known Activations