© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7011
    Prev
    Next
    INDEX
    Explanations

    possessive 's

    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
    大åݦ
    -0.09
     stereotype
    -0.09
    æĢ¥äºİ
    -0.09
    诽
    -0.09
    é©°
    -0.09
    éģij
    -0.08
    à¸IJาà¸Ļ
    -0.08
    å¥Ķ
    -0.08
    èIJ½ä¸ĭ
    -0.08
    æĻģ
    -0.08
    POSITIVE LOGITS
     gone
    0.10
    lass
    0.09
    gone
    0.09
    .hd
    0.09
    olate
    0.08
    åįļ客
    0.08
    认å®ļ
    0.08
    anse
    0.08
    åįģåħŃæĿ¡
    0.08
    ÙĪاب
    0.08
    Activations Density 0.062%

    No Known Activations