© 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. 6835
    Prev
    Next
    INDEX
    Explanations

    just in time or case

    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
    ä¸Ģç»ı
    -0.12
    çij¾
    -0.10
    Intialized
    -0.09
    ê·¹
    -0.09
    çļ¿
    -0.09
    å±ħ
    -0.09
    ONGL
    -0.09
    -chan
    -0.08
    æī¹
    -0.08
    äºĨä»ĸçļĦ
    -0.08
    POSITIVE LOGITS
    efore
    0.10
    _coeffs
    0.10
    赶æĿ¥
    0.09
    æľīåĩłä¸ª
    0.09
    笼
    0.09
    åģļä¸ĢäºĽ
    0.08
     shredded
    0.08
    urge
    0.08
    Tier
    0.08
    éĴ´
    0.08
    Activations Density 0.011%

    No Known Activations