© 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. 9381
    Prev
    Next
    INDEX
    Explanations

    free text, free form, free of

    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··
    -0.11
    æĹłå£°
    -0.10
    åħĶ
    -0.09
    odus
    -0.09
    ç´§æĢ¥
    -0.09
    åīĶ
    -0.09
    èĢ½è¯¯
    -0.09
    ITER
    -0.09
     lá»Ļ
    -0.09
    ãĥĬãĥ«
    -0.08
    POSITIVE LOGITS
    èĩªåľ¨
    0.16
    èĩªçĶ±
    0.13
     freely
    0.11
     fre
    0.11
    fre
    0.10
    é©°
    0.10
    free
    0.10
    Fre
    0.10
     Ñģвобод
    0.10
    yte
    0.09
    Activations Density 0.091%

    No Known Activations