© 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. 38812
    Prev
    Next
    INDEX
    Explanations

    foreign words and phrases

    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
    ingham
    -0.09
    éķĹ
    -0.09
     Falk
    -0.09
    ç»ıèIJ¥
    -0.08
    .pb
    -0.08
    æı£
    -0.08
     Supports
    -0.08
    Reminder
    -0.08
    _stub
    -0.08
    åħį责声æĺİ
    -0.08
    POSITIVE LOGITS
    亲åĪĩ
    0.10
    æ¸İ
    0.09
    ather
    0.09
    åħ¨å¤©
    0.09
    è¡Įäºĭ
    0.09
    åĭ¤åĬ³
    0.08
    éĹ³
    0.08
    ä»İ严
    0.08
    çĸł
    0.08
    äºĨåIJĹ
    0.08
    Activations Density 0.006%

    No Known Activations