© 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. 7903
    Prev
    Next
    INDEX
    Explanations

    ah, ahh, exclamation

    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
    éŃħ
    -0.10
    oger
    -0.09
    åIJ¬äºĨ
    -0.09
    ç¢ļ
    -0.09
    essional
    -0.08
    æĿµ
    -0.08
    西æ´ĭ
    -0.08
     Cooke
    -0.08
    ypes
    -0.08
    ared
    -0.08
    POSITIVE LOGITS
    çķ
    0.12
    èĢķåľ°
    0.11
    ä¸ĢåĪ»
    0.10
    èĥĦ
    0.10
    åĬij
    0.09
    åĬ¬
    0.09
    ement
    0.09
    æĹ¶æľº
    0.09
    Parcel
    0.09
    çļĦåĬŀæ³ķ
    0.09
    Activations Density 0.009%

    No Known Activations