© 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. 37487
    Prev
    Next
    INDEX
    Explanations

    full time or full completion

    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
    头æĿ¡
    -0.10
    å¼Ń
    -0.09
     Ingen
    -0.09
    alus
    -0.08
    å®ŀäºĭæ±Ĥ
    -0.08
    è¡Ķ
    -0.08
    éĩįéĩį
    -0.08
    isl
    -0.08
     ace
    -0.08
    带ä¸Ĭ
    -0.08
    POSITIVE LOGITS
    æķĿ
    0.10
    éĩİçĶŁ
    0.09
    海峡
    0.09
    交ä»ĺ
    0.08
    åħ¬ç¤¾
    0.08
    èĩ£
    0.08
    è§īå¾Ĺ
    0.08
    é©»
    0.08
    æĢ»åħ¬åı¸
    0.08
    éĻĮçĶŁ
    0.08
    Activations Density 0.015%

    No Known Activations