© 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. 31140
    Prev
    Next
    INDEX
    Explanations

    seeing

    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
    stell
    -0.11
    ulus
    -0.09
    pak
    -0.08
    åľºåIJĪ
    -0.08
    ìĽĢ
    -0.08
     опÑĭÑĤ
    -0.08
    份
    -0.08
    poster
    -0.08
    Äĥn
    -0.08
    iss
    -0.08
    POSITIVE LOGITS
    éĢı
    0.10
    å¾Ģäºĭ
    0.10
    ðŁijĢ
    0.10
    çľĭåĩº
    0.09
    éĶ¯
    0.09
    æĥļ
    0.09
    鸳
    0.09
    æ
    0.09
    çľĭæ¸ħ
    0.09
    éĽ¾
    0.09
    Activations Density 0.039%

    No Known Activations