© 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. 7801
    Prev
    Next
    INDEX
    Explanations

    nib sizes

    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
    è¢Ĵ
    -0.10
    lice
    -0.09
    é£İä¿Ĺ
    -0.09
    åĬ¨åijĺ
    -0.09
     taped
    -0.09
    éĿ¢åŃĶ
    -0.09
    å¤©çľŁ
    -0.08
    èĢĻ
    -0.08
    æĪij们就
    -0.08
    ä¸Ģç¬ij
    -0.08
    POSITIVE LOGITS
    åĨĻåŃĹ
    0.16
    ç¬Ķ
    0.15
     ink
    0.13
    书åĨĻ
    0.12
     pen
    0.12
    pen
    0.12
     fountain
    0.12
    墨
    0.11
     Writers
    0.11
    çłļ
    0.11
    Activations Density 0.055%

    No Known Activations