© 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. 38120
    Prev
    Next
    INDEX
    Explanations

    each or every

    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
    affles
    -0.10
    lah
    -0.09
    reate
    -0.08
    åĽłä¸ºåľ¨
    -0.08
    Bru
    -0.08
    amba
    -0.07
    lus
    -0.07
    ä¸ŃéĢĶ
    -0.07
    orro
    -0.07
    town
    -0.07
    POSITIVE LOGITS
    æ¯ı个
    0.38
     each
    0.37
    each
    0.33
    æ¯ıä¸Ģ
    0.33
     каждой
    0.32
    æ¯ıä¸Ģ个
    0.31
    æ¯ıåĢĭ
    0.31
     каждого
    0.30
    Each
    0.27
     Each
    0.27
    Activations Density 0.316%

    No Known Activations