© 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. 61033
    Prev
    Next
    INDEX
    Explanations

    taking too long

    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
    вол
    -0.09
    èIJ¥åĪ©
    -0.09
    éľĩ
    -0.09
    æIJĶ
    -0.09
    åºĶåıĬæŶ
    -0.09
    à¹ģà¸Ĺà¸Ļ
    -0.08
    æİ¥å¾ħ
    -0.08
    ä¸ºæľŁ
    -0.08
    尺度
    -0.08
     tempor
    -0.08
    POSITIVE LOGITS
    å¤ĸåĽ´
    0.10
    åĢĶ
    0.09
     conservative
    0.08
     fa
    0.08
    åºķèķ´
    0.08
    å°¤åħ¶æĺ¯
    0.08
    ä½ĵéĩı
    0.08
     занÑıÑĤ
    0.08
    è¦ģ
    0.08
    èIJ¦
    0.08
    Activations Density 0.090%

    No Known Activations