© 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. 4781
    Prev
    Next
    INDEX
    Explanations

    article, title, or proper noun following punctuation

    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
    èĤĭ
    -0.10
    å¾Ĵ
    -0.10
    éĺµèIJ¥
    -0.09
    槲
    -0.09
     CORPOR
    -0.09
    让æĤ¨
    -0.09
    æ¹ĸ人
    -0.08
    _SA
    -0.08
    plier
    -0.08
    еÑģÑĤÑĮ
    -0.08
    POSITIVE LOGITS
     a
    0.09
    اعت
    0.09
    gem
    0.09
    对æѤ
    0.09
    çĽ¯
    0.08
    rack
    0.08
    åĪĨ管
    0.08
    çĭİ
    0.08
    äºĭãģĮ
    0.08
     Adv
    0.07
    Activations Density 0.040%

    No Known Activations