© 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. 31224
    Prev
    Next
    INDEX
    Explanations

    awards and prizes

    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
    çľģåĨħ
    -0.09
    ç»ı纪人
    -0.09
    大海
    -0.09
    åIJIJ
    -0.09
    sek
    -0.09
    æŬ
    -0.09
    è¿Ľåľº
    -0.09
    æݸ
    -0.08
    uder
    -0.08
    unds
    -0.08
    POSITIVE LOGITS
    ç§ijæĬĢåĪĽæĸ°
    0.09
    å°ıåŃIJ
    0.09
    æħĪåĸĦ
    0.09
     пеÑĢем
    0.09
    æ»ĭåij³
    0.09
    éĻĦåĬł
    0.09
    æ®ĸ
    0.09
    å²ĺ
    0.08
    _cod
    0.08
     McCabe
    0.08
    Activations Density 0.207%

    No Known Activations