© 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. 9090
    Prev
    Next
    INDEX
    Explanations

    shipping and orders

    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
    æ¹¾
    -0.10
    æīĭä¸ŃçļĦ
    -0.09
     ult
    -0.08
    comm
    -0.08
    å°¼äºļ
    -0.08
     ØŃص
    -0.08
    queeze
    -0.08
    jej
    -0.08
     behalf
    -0.08
     Hob
    -0.08
    POSITIVE LOGITS
    æݨåIJij
    0.10
    åIJĽ
    0.10
    èı©æıIJ
    0.10
    çĬģ
    0.10
    è·¨è¶Ĭå¼ı
    0.09
    çĻ½è¡£
    0.09
    åĸĬ
    0.09
    ä¸įèĥ½åĨį
    0.09
    iless
    0.08
    åIJ
    0.08
    Activations Density 0.048%

    No Known Activations