© 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. 23213
    Prev
    Next
    INDEX
    Explanations

    remedy

    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
    aqu
    -0.10
    å¶
    -0.09
    atinum
    -0.09
    eri
    -0.09
    mare
    -0.09
    apo
    -0.09
    æŁ¿
    -0.09
    å¼ģ
    -0.09
     fancy
    -0.09
    éģIJ
    -0.08
    POSITIVE LOGITS
    æݪæĸ½
    0.12
    ì±ħ
    0.09
    ä¸įäºĨ
    0.09
    èĹľ
    0.09
    åļ¼
    0.09
    åŃ³
    0.09
     overcrow
    0.08
    izin
    0.08
    èĺħ
    0.08
    ry
    0.08
    Activations Density 0.014%

    No Known Activations