© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7661
    Prev
    Next
    INDEX
    Explanations

    trademarks or registered trademarks

    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
     trần
    -0.10
    妥
    -0.09
    å¤Ļ
    -0.08
    ä¼ı
    -0.08
    æĸ½å±ķ
    -0.08
    zer
    -0.08
    éĺ¶æ¢¯
    -0.08
    èµĮåįļ
    -0.08
    ovan
    -0.08
     chances
    -0.08
    POSITIVE LOGITS
    _CTL
    0.10
     babel
    0.09
    ICT
    0.09
    è°ħ解
    0.09
     поÑģл
    0.09
     Phelps
    0.09
    è®®äºĭ
    0.09
     اÙĦشر
    0.08
    åł
    0.08
    ä¸į说
    0.08
    Activations Density 0.001%

    No Known Activations