© 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. 35551
    Prev
    Next
    INDEX
    Explanations

    the catch

    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
    ë¡Ŀ
    -0.09
    agnostics
    -0.08
    éĶ¦
    -0.08
    .SetValue
    -0.08
     deltas
    -0.08
    èµ·æĿ¥
    -0.08
    .GetValue
    -0.08
    åºı
    -0.08
    .GetName
    -0.08
    ØŃÙĨ
    -0.08
    POSITIVE LOGITS
    ä¸įæ¸ħ
    0.10
    itat
    0.09
    CNT
    0.09
    çīµæīĭ
    0.09
    æĢ§å¼º
    0.09
    ANC
    0.08
    æľ¬ç½ij
    0.08
    ichten
    0.08
    اÙħر
    0.08
    æĹĥ
    0.08
    Activations Density 0.025%

    No Known Activations