© 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. 58431
    Prev
    Next
    INDEX
    Explanations

    organized by

    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
    åįĴ
    -0.09
    åij¦
    -0.09
    裨
    -0.08
    NIL
    -0.08
     verst
    -0.08
    æĭ¾
    -0.08
    èĥ½åĬĽå¼º
    -0.08
    çī¹éķ¿
    -0.08
     Mum
    -0.08
    .TODO
    -0.08
    POSITIVE LOGITS
    æĺ¯çĶ±
    0.11
    çĶ±
    0.10
    éļ¶å±ŀäºİ
    0.10
     oleh
    0.09
    åĪ¶éĢłåķĨ
    0.09
     بÙĪاسطة
    0.09
    主åĬŀ
    0.09
    ìĤ½
    0.09
    managed
    0.09
    好äºĨ
    0.09
    Activations Density 0.152%

    No Known Activations