© 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. 10502
    Prev
    Next
    INDEX
    Explanations

    GPL LGPL license

    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
    ç¡ķ
    -0.09
     Interrupt
    -0.09
    URT
    -0.08
    Powered
    -0.08
    лÑĥ
    -0.08
    ector
    -0.08
    ä¿Ŀåģ¥
    -0.08
    被åĪ¤
    -0.08
    packing
    -0.08
     precaution
    -0.08
    POSITIVE LOGITS
    zet
    0.10
    dle
    0.10
    éĢģåĩº
    0.10
    æĺ¯å¯¹
    0.10
    /lic
    0.10
    å±Ĥå±Ĥ
    0.09
    arie
    0.09
    ัส
    0.09
    æĭ¿åĩºæĿ¥
    0.09
     Kok
    0.09
    Activations Density 0.428%

    No Known Activations