© 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. 26495
    Prev
    Next
    INDEX
    Explanations

    collection

    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
    ungs
    -0.09
    .setTag
    -0.09
    ажд
    -0.09
     Fresh
    -0.09
    ä¸Ģç¯ĩ
    -0.09
    .FILE
    -0.08
    æĥ³åİ»
    -0.08
    éĴ»çŁ³
    -0.08
    pedo
    -0.08
     fatally
    -0.08
    POSITIVE LOGITS
    æĶ¶éĽĨ
    0.11
    çĻĸ
    0.11
    åĵģ
    0.10
    ä¸įæĸŃå¢ŀåĬł
    0.09
     collecting
    0.09
    æ³¥åľŁ
    0.09
    Collect
    0.09
    åIJĦå¼ı
    0.09
    çĤ¹æ»´
    0.09
    åIJĦå¼ıåIJĦæł·
    0.08
    Activations Density 0.041%

    No Known Activations