© 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. 19432
    Prev
    Next
    INDEX
    Explanations

    scores and points difference

    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
    鲤
    -0.09
    大éĻĨ
    -0.09
    饱满
    -0.08
    éľ²å¤©
    -0.08
    æĿ°
    -0.08
    PLIER
    -0.08
    ัà¸Ķ
    -0.08
    éªIJ
    -0.08
    orry
    -0.08
    หาร
    -0.08
    POSITIVE LOGITS
    difference
    0.11
     difference
    0.11
    æĬµæĬĹåĬĽ
    0.10
    Compiled
    0.09
    IgnoreCase
    0.09
    å·®
    0.09
    éĢĿ
    0.09
    å·®è·Ŀ
    0.09
    BN
    0.08
    ottes
    0.08
    Activations Density 0.020%

    No Known Activations