© 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. 11892
    Prev
    Next
    INDEX
    Explanations

    and followed by auxiliary verbs

    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
    æľĢå¿«
    -0.09
    å¥Ĺ
    -0.08
    /popper
    -0.08
     ghé
    -0.08
    _formula
    -0.08
    Ƭ
    -0.08
    绪
    -0.08
    วà¸Ļ
    -0.08
    _pdata
    -0.08
    dealloc
    -0.08
    POSITIVE LOGITS
    antar
    0.09
    æ³°
    0.09
    ä¸ļ
    0.09
    ãģłãĤįãģĨ
    0.09
    ane
    0.09
    sg
    0.09
    çİ°åŃĺ
    0.08
    ä¸įè¡Į
    0.08
     PAD
    0.08
    enties
    0.08
    Activations Density 0.091%

    No Known Activations