© 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. 56147
    Prev
    Next
    INDEX
    Explanations

    make money

    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
     cert
    -0.09
    cert
    -0.08
    æ¸Ĺ
    -0.08
     ÑĤоÑĢ
    -0.08
     Cert
    -0.08
    éŀŃ
    -0.08
    Cert
    -0.08
    çĹ´
    -0.08
    iten
    -0.08
    æ·Į
    -0.08
    POSITIVE LOGITS
    交éĶĻ
    0.10
    anie
    0.10
    å®ļçĤ¹
    0.09
    /XML
    0.09
    å¼ĢäºĨ
    0.09
    ä¸ĭ称
    0.09
    @js
    0.09
    Edition
    0.09
    æĭ¿äºĨ
    0.09
    ä¸į便
    0.09
    Activations Density 0.080%

    No Known Activations