© 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. 47864
    Prev
    Next
    INDEX
    Explanations

    printing and publishing

    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
     заÑĢегиÑģÑĤÑĢи
    -0.09
    æŁ¥çľĭæĽ´å¤ļ
    -0.08
    ä¼ļ议室
    -0.08
     há»ĵ
    -0.08
    弯
    -0.08
    çĤ¹èµŀ
    -0.07
    .randrange
    -0.07
    izza
    -0.07
    wä
    -0.07
    AREA
    -0.07
    POSITIVE LOGITS
    åį°åĪ·
    0.13
    åĩºçīĪ
    0.12
    åıijè¡Į
    0.12
    å·´é»İ
    0.11
    åĪĬ
    0.11
    åĶ®åįĸ
    0.11
    çīĪ
    0.10
    æĬij
    0.09
    åĶ®
    0.09
    æĪIJåĵģ
    0.09
    Activations Density 0.105%

    No Known Activations