© 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. 39866
    Prev
    Next
    INDEX
    Explanations

    race walk distance

    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
     kê
    -0.10
    åł°
    -0.09
    èĬĤæĹ¥
    -0.09
    å¾Ģå¤ĸ
    -0.09
    -inverse
    -0.09
    ãģĮãĤī
    -0.09
    éľĨ
    -0.09
    çĶŁæ®ĸ
    -0.08
    topl
    -0.08
    indx
    -0.08
    POSITIVE LOGITS
    è·ijäºĨ
    0.10
     ribbon
    0.09
    .runners
    0.09
    zin
    0.09
    æŃ£å¼ı
    0.09
    CCA
    0.09
    haft
    0.08
    éļ¶
    0.08
    举
    0.08
    åİ¿éķ¿
    0.08
    Activations Density 0.143%

    No Known Activations