© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 27737
    Prev
    Next
    INDEX
    Explanations

    try and verb

    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
    åĵĩ
    -0.09
    æĸĹ
    -0.09
    澡
    -0.08
    راÙĨ
    -0.08
    infeld
    -0.08
    ADM
    -0.08
    idon
    -0.08
    _assigned
    -0.08
    çĻ½æ²Ļ
    -0.08
    ãģĦãģ¤
    -0.07
    POSITIVE LOGITS
    amp
    0.10
    大家åĪĨ享
    0.10
    åľ¨è¿Ļç§į
    0.09
    麽
    0.09
    ä½Ī
    0.09
    alous
    0.09
    verter
    0.08
    èĩªå·±åĸľæ¬¢
    0.08
    åĪ«äºº
    0.08
    /OR
    0.08
    Activations Density 0.008%

    No Known Activations