© 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. 59005
    Prev
    Next
    INDEX
    Explanations

    how to

    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
    zin
    -0.10
    åł¡
    -0.09
    ç»ı
    -0.09
    ëĬIJ
    -0.08
    çݯå¢ĥä¸Ń
    -0.08
    Sher
    -0.08
    ä¸Ģè·¯
    -0.08
     bare
    -0.08
    ç¶ĵ
    -0.08
     Sche
    -0.08
    POSITIVE LOGITS
    æįŁ
    0.10
    çļĦæł·åŃIJ
    0.09
    åŁł
    0.09
    èĿİ
    0.09
    _SA
    0.09
    FLOW
    0.09
    声åĵį
    0.09
    _locs
    0.09
    éļ¼
    0.09
    å¸Ľ
    0.08
    Activations Density 0.117%

    No Known Activations