© 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. 53871
    Prev
    Next
    INDEX
    Explanations

    sizes and conservation

    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
    辨
    -0.09
    oka
    -0.09
    ä¼ģ
    -0.09
    æĪIJåĬŁçİĩ
    -0.09
    endar
    -0.08
    è¿ĺä¸įéĶĻ
    -0.08
    oeff
    -0.08
    ç¼ī
    -0.08
    /ar
    -0.08
    ä¾ĭè¡Į
    -0.08
    POSITIVE LOGITS
    çķ¸å½¢
    0.09
     Carson
    0.09
     Crest
    0.09
    å¥Ħ
    0.09
     sizes
    0.09
    sizes
    0.08
    è§Ħæł¼
    0.08
    æ¡Ĥ
    0.08
    èĦĴ
    0.08
    ambia
    0.08
    Activations Density 0.033%

    No Known Activations