© 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. 4753
    Prev
    Next
    INDEX
    Explanations

    MG Road, Simone, Report

    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
     Ñģебе
    -0.09
    itat
    -0.09
    æ¦ķ
    -0.08
    kke
    -0.08
    éĻĪåĪĹ
    -0.08
    avn
    -0.08
    åĪĨ红
    -0.08
    ugin
    -0.08
    ç´«å¤ĸ线
    -0.08
    ulator
    -0.08
    POSITIVE LOGITS
    ä»Ģä¹Īåľ°æĸ¹
    0.10
    æľĭ
    0.10
    纤
    0.09
    ë£Į
    0.09
    线ä¸ĭ
    0.08
    æĭīæĸ¯
    0.08
    éĤ£ä¹Ī容æĺĵ
    0.08
     ``(
    0.08
    åĵĪå°Ķ
    0.08
    åłµå¡ŀ
    0.08
    Activations Density 0.002%

    No Known Activations