© 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. 36841
    Prev
    Next
    INDEX
    Explanations

    published information

    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
    plode
    -0.10
    éĬ®
    -0.10
    blo
    -0.09
    çľ¼çķĮ
    -0.09
    Publication
    -0.09
    èĵį
    -0.09
    æĸĩåĮĸåºķèķ´
    -0.09
    idar
    -0.08
     Subjects
    -0.08
     Dor
    -0.08
    POSITIVE LOGITS
    äºĨä»ĸçļĦ
    0.10
    ABLE
    0.09
    (crate
    0.09
    äºĨä¸Ģç³»åĪĹ
    0.09
    æ¶Īæģ¯ç§°
    0.09
    ables
    0.09
    äºĨèĩªå·±çļĦ
    0.09
    让æ¶Īè´¹èĢħ
    0.08
    ä¸įåĩºæĿ¥
    0.08
    izable
    0.08
    Activations Density 0.054%

    No Known Activations