© 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. 22771
    Prev
    Next
    INDEX
    Explanations

    Phabricator, Phrack, PhoN, phloem

    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
    oint
    -0.10
    åĭ¤å¥ĭ
    -0.08
    ivi
    -0.08
    ÄĻd
    -0.08
    èĺijèıĩ
    -0.08
    .Reporting
    -0.08
    æĤĶ
    -0.08
    sip
    -0.08
    é£İåħī
    -0.08
    éķ¿æķĪ
    -0.08
    POSITIVE LOGITS
    æĦĪ
    0.10
     todd
    0.09
    WARE
    0.09
    æĹĦ
    0.09
    sters
    0.09
    éĤ°
    0.09
    éric
    0.09
    æŶæĬ¥
    0.09
    èĢģ人家
    0.08
    è¡Ļ
    0.08
    Activations Density 0.033%

    No Known Activations