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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21123
    Prev
    Next
    INDEX
    Explanations

    nearly half of

    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
    issen
    -0.09
    **)&
    -0.09
    aml
    -0.09
    ivité
    -0.09
    ä¹ħäºĨ
    -0.08
    åŃĶéĽĢ
    -0.08
    .MSG
    -0.08
     côt
    -0.08
    Castle
    -0.08
    avings
    -0.08
    POSITIVE LOGITS
    æ³
    0.10
    ä¹ĥèĩ³
    0.09
    çļĦå¢ŀéķ¿
    0.08
    èĪªè¡Į
    0.08
    thest
    0.08
     piv
    0.08
    æł¹æľ¬ä¸į
    0.08
    æĺ¯çĶ¨æĿ¥
    0.08
    å½ĵåīį
    0.08
    ä¸Ģ个å¤ļ
    0.08
    Activations Density 0.023%

    No Known Activations