© 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. 27839
    Prev
    Next
    INDEX
    Explanations

    Retro copyright

    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
    -ng
    -0.10
    áºłI
    -0.09
    éĭª
    -0.09
    æĶ¾åľ¨
    -0.08
    æĸ°æĹ¶ä»£
    -0.08
    ILER
    -0.08
    ages
    -0.08
    æĶ¾ç½®
    -0.08
    /templates
    -0.08
     поÑģл
    -0.08
    POSITIVE LOGITS
    é¢ijé¢ij
    0.09
    ç»ıæŁ¥
    0.08
    åıªåī©ä¸ĭ
    0.08
    èĮ¹
    0.08
     Retro
    0.08
    产çĶŁ
    0.08
    æĺ¯åĽ½åĨħ
    0.08
     remaining
    0.08
    åIJĦé¡¹å·¥ä½ľ
    0.08
    nel
    0.08
    Activations Density 0.020%

    No Known Activations