© 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. 33604
    Prev
    Next
    INDEX
    Explanations

    quote or estimate

    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
    miss
    -0.09
    ister
    -0.08
    æĹłæĦı
    -0.08
    çĿĢä»ĸ
    -0.08
    ém
    -0.08
    骨骼
    -0.08
    æķ£
    -0.08
    cad
    -0.08
    HTML
    -0.07
    ISTER
    -0.07
    POSITIVE LOGITS
    ÑģÑĤоÑı
    0.10
    é¼»åŃIJ
    0.10
    人åĿĩ
    0.10
    äºĪ
    0.10
    å¹³åĿĩæ°´å¹³
    0.09
    ë°Ľ
    0.09
    åĨĬ
    0.09
    ç¬ij声
    0.09
    æĶ¶åĪ°
    0.09
    æĪijçľĭ
    0.09
    Activations Density 0.010%

    No Known Activations