© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51859
    Prev
    Next
    INDEX
    Explanations

    then

    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¸İåIJ¦
    -0.10
    ä¿Ĺ
    -0.09
    âĦħ
    -0.09
    UNG
    -0.09
    uries
    -0.08
    çķĻè¨ĢæĿ¿
    -0.08
    涯
    -0.08
    çļĦ积æŀģæĢ§
    -0.08
    riers
    -0.08
     Ñģобой
    -0.08
    POSITIVE LOGITS
    èĢĮåIJİ
    0.24
    çĦ¶åIJİ
    0.23
     followed
    0.22
    æİ¥çĿĢ
    0.20
    åĨįåĪ°
    0.20
     заÑĤем
    0.19
     rá»ĵi
    0.18
    ç´§æİ¥çĿĢ
    0.18
     Ø«Ùħ
    0.17
    è¿ĽèĢĮ
    0.17
    Activations Density 0.237%

    No Known Activations