© 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. 36098
    Prev
    Next
    INDEX
    Explanations

    without notice or explanation

    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
    oner
    -0.10
    èĭį
    -0.09
    6
    -0.08
    æĹ©æĻļ
    -0.08
    LOGIN
    -0.08
    åıijçİ°
    -0.08
    7
    -0.08
    Instr
    -0.08
    9
    -0.08
    è¿ĺä¼ļ
    -0.08
    POSITIVE LOGITS
    åıĸåĨ³
    0.11
    çĤ¹åĩ»æŁ¥çľĭ
    0.10
    çĶ»çĶ»
    0.10
    ä¾Ŀæ³ķ追究
    0.09
    çļĦä¸Ģ项
    0.09
    尤为
    0.09
    åĽ½èµĦ
    0.09
     ê²°
    0.09
     Hague
    0.09
    ç«Ļ
    0.09
    Activations Density 0.001%

    No Known Activations