© 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. 20403
    Prev
    Next
    INDEX
    Explanations

    open source software package

    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
    æĪij对
    -0.09
    town
    -0.08
    سائÙĦ
    -0.08
    setter
    -0.08
    å»ī
    -0.08
    åįĹæĸ¹
    -0.07
    æIJŀ好
    -0.07
    çĥŁ
    -0.07
    _budget
    -0.07
    UFF
    -0.07
    POSITIVE LOGITS
    éªĪ
    0.09
    è¡ĮåĬ¨è®¡åĪĴ
    0.09
    imary
    0.09
    æĭ¥æľī
    0.09
    娱ä¹IJå¹³åı°
    0.09
    ASSES
    0.09
    æĹĹèĪ°
    0.09
    ä¸įåħĭ
    0.09
    æĪIJç«ĭäºİ
    0.09
    çĸļ
    0.09
    Activations Density 0.350%

    No Known Activations