© 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. 16962
    Prev
    Next
    INDEX
    Explanations

    alphanumeric codes

    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
    åĵĨ
    -0.09
    æĽ´ä½İ
    -0.09
    urai
    -0.09
    æ¸ļ
    -0.09
    æĬķ
    -0.08
    .dex
    -0.08
    uala
    -0.08
    ities
    -0.08
    FOX
    -0.08
    (da
    -0.08
    POSITIVE LOGITS
    a
    0.10
    s
    0.09
    ing
    0.09
    è°
    0.08
     cli
    0.08
    e
    0.08
    iets
    0.08
    éĿ¢èī²
    0.08
    afe
    0.08
    çļĦ好å¤Ħ
    0.08
    Activations Density 0.211%

    No Known Activations