© 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. 56234
    Prev
    Next
    INDEX
    Explanations

    duration/time measurement

    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
    rys
    -0.12
    ÑĢаÐ
    -0.11
    èªķ
    -0.10
    èĭ¥å¹²
    -0.10
    åıŁ
    -0.09
    éķIJ
    -0.09
    åħĪ天
    -0.09
    /goto
    -0.09
    è¶ĬæĿ¥è¶Ĭå¤ļ
    -0.09
    èµ·æŃ¥
    -0.09
    POSITIVE LOGITS
     ago
    0.14
    åģľçķĻåľ¨
    0.11
    å¿į
    0.10
    ago
    0.10
    ä¿ĿæĮģ
    0.09
     Ago
    0.09
    unc
    0.09
    缸èģļ
    0.08
    -lived
    0.08
    ä»ĺãģįåIJĪ
    0.08
    Activations Density 0.063%

    No Known Activations