© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8103
    Prev
    Next
    INDEX
    Explanations

    strict code semicolon

    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
    æįı
    -0.10
    çŁ£
    -0.09
    åŀ«
    -0.09
    å¥ł
    -0.09
    åıĮæĸ¹
    -0.09
    éºĴéºŁ
    -0.09
    IOC
    -0.09
     nevertheless
    -0.09
    è¯įè¯Ń
    -0.09
    _PAD
    -0.08
    POSITIVE LOGITS
    åIJ¬èµ·æĿ¥
    0.09
    remen
    0.09
    éŃģ
    0.08
    oris
    0.08
    æ²Ļ
    0.08
    çīĽ
    0.08
    éĢ¡
    0.08
     Mits
    0.08
    inges
    0.08
    æ¾İæ¹ĥ
    0.08
    Activations Density 0.005%

    No Known Activations