© 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. 63265
    Prev
    Next
    INDEX
    Explanations

    Add, mix, place, mixed

    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
    æĢ¨
    -0.09
     Murdoch
    -0.09
    Ùģار
    -0.09
    æ·±è¿ľ
    -0.09
    éĶ»çĤ¼
    -0.08
    è·¨çķĮ
    -0.08
    inan
    -0.08
    è¿ľæĸ¹
    -0.08
    deen
    -0.08
     Celt
    -0.08
    POSITIVE LOGITS
    åĬłåħ¥
    0.12
    åĬłåħ¥äºĨ
    0.10
    ä¸ĢæŃ¥ä¸ĢæŃ¥
    0.09
    çļ±
    0.09
    nt
    0.09
    çĶ·çĶŁ
    0.09
    ä¹ŀ
    0.08
    æıIJ款
    0.08
    Tween
    0.08
    å¢ŀéĩı
    0.08
    Activations Density 0.005%

    No Known Activations