© 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. 54234
    Prev
    Next
    INDEX
    Explanations

    one another

    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
    æĶ¾å¼Ģ
    -0.10
    失
    -0.09
    iju
    -0.09
    åĺĪ
    -0.09
    çļĦåį°è±¡
    -0.08
    Č
    -0.08
    讨åİĮ
    -0.08
    ä¹Łä¸įåı¯èĥ½
    -0.08
    ç¬Ķè®°æľ¬
    -0.08
    æĹ¢æľī
    -0.08
    POSITIVE LOGITS
    御
    0.09
    aura
    0.08
    åĵī
    0.08
    мÑĭÑĪ
    0.08
     Barth
    0.08
    urope
    0.08
    à¹Īาว
    0.08
     Yap
    0.08
    adder
    0.08
    ä¹ħä¹ħ
    0.08
    Activations Density 0.031%

    No Known Activations