© 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. 52240
    Prev
    Next
    INDEX
    Explanations

    reporting news or events

    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
    æłijç«ĭ
    -0.11
    建åĨĽ
    -0.09
    è¡Įèµ°
    -0.09
    atab
    -0.08
    jer
    -0.08
    éºĴéºŁ
    -0.08
    æ¦ľ
    -0.08
    æ¦Ń
    -0.08
    æĬĢæľ¯åĪĽæĸ°
    -0.08
    äºĭä¸ļ
    -0.08
    POSITIVE LOGITS
    æĬ¥éģĵ
    0.10
    羣çļ®
    0.10
    oped
    0.10
    åł±å°İ
    0.10
     reporter
    0.10
     reporters
    0.10
    è¨ĺèĢħ
    0.09
    .Reporting
    0.09
    åijĺ
    0.09
    _ENTER
    0.09
    Activations Density 0.018%

    No Known Activations