© 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. 35460
    Prev
    Next
    INDEX
    Explanations

    a noun

    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
    æŁIJäºĽ
    -0.11
    éĤ£æł·çļĦ
    -0.10
    æľī人说
    -0.09
    èİ«è¿ĩäºİ
    -0.09
    éĤ£æł·
    -0.09
    æŁĶ
    -0.08
     certain
    -0.08
    è°ĵ
    -0.08
     somew
    -0.08
    èĪ¬
    -0.08
    POSITIVE LOGITS
    ISCO
    0.10
    ouse
    0.09
    åİĨ
    0.09
    çĵľ
    0.08
    ansa
    0.08
    æĻı
    0.08
    AEA
    0.08
    äºĶå®ĺ
    0.08
    ä¹ĭæīĢ以
    0.08
    çİ°æľīçļĦ
    0.08
    Activations Density 0.035%

    No Known Activations