© 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. 4445
    Prev
    Next
    INDEX
    Explanations

    deal with situations

    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
    emer
    -0.11
    çĺŁ
    -0.10
    ined
    -0.09
    uated
    -0.09
    rimp
    -0.08
     kenn
    -0.08
     Kurd
    -0.08
    æ¸ļ
    -0.08
    æľīä¸įåIJĮçļĦ
    -0.08
     Paras
    -0.08
    POSITIVE LOGITS
    åºĶ对
    0.12
    åºĶä»ĺ
    0.10
    zar
    0.09
    对ä»ĺ
    0.09
     zar
    0.09
    éĿ¢å¯¹
    0.09
    /mit
    0.09
    æIJŀå®ļ
    0.09
    ibel
    0.09
    è¿İ
    0.08
    Activations Density 0.204%

    No Known Activations