© 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. 26680
    Prev
    Next
    INDEX
    Explanations

    attitude, disposition, demeanor

    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
    ä¸ĢåĪ»
    -0.10
     à¹Ĩ
    -0.09
    efault
    -0.09
    å¾Ī大
    -0.08
    æĦıæĢĿ
    -0.08
    读æĩĤ
    -0.08
    ido
    -0.08
    ãĤĪãģĨãģª
    -0.08
    ness
    -0.08
    åĬŀæ³ķ
    -0.08
    POSITIVE LOGITS
    åIJĦå¼Ĥ
    0.15
    ä¸įä½³
    0.13
    ä¸Ĭæľī
    0.10
    åıĺè¿ģ
    0.10
    åıĺåĮĸ
    0.09
    èľľ
    0.09
    æģ¶åĬ£
    0.09
    çĤİ
    0.09
    çļĦåıĺåĮĸ
    0.09
    è¿ĺä¸įéĶĻ
    0.09
    Activations Density 0.133%

    No Known Activations