© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52614
    Prev
    Next
    INDEX
    Explanations

    power play goals / one on one

    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
    æijĬ
    -0.09
    EEP
    -0.09
    æİĢ
    -0.09
    æĸĩçĮ®
    -0.08
    нÑĭ
    -0.08
     Murphy
    -0.08
    æIJŃæ¡£
    -0.08
    ä¸įè¿ĩæĺ¯
    -0.08
    aman
    -0.07
    ç¿ħ
    -0.07
    POSITIVE LOGITS
    .deb
    0.09
    æ¿®
    0.09
    çĵ¢
    0.09
    APE
    0.09
    ACHI
    0.09
    åĽŀæĶ¶
    0.09
    ç»ıå¼Ģ
    0.09
     Brom
    0.08
    .PerformLayout
    0.08
    æľĪ以æĿ¥
    0.08
    Activations Density 0.010%

    No Known Activations