© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 48630
    Prev
    Next
    INDEX
    Explanations

    last minute deals and notice

    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
    é¢ĦåħĪ
    -0.10
    ayed
    -0.09
    itional
    -0.08
    ayer
    -0.08
    iston
    -0.08
    ä¸ŃéĢĶ
    -0.08
    /he
    -0.07
    ä¸Ģå®ļçļĦ
    -0.07
    /be
    -0.07
    æĮ¯åħ´
    -0.07
    POSITIVE LOGITS
    aneously
    0.12
    赶æĿ¥
    0.11
    å¤Ķ
    0.10
    -ish
    0.10
    襲
    0.10
    aurant
    0.10
    ilers
    0.10
    STYPE
    0.10
    /Internal
    0.10
    اس
    0.09
    Activations Density 0.003%

    No Known Activations