© 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. 38571
    Prev
    Next
    INDEX
    Explanations

    explaining the situation

    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
    è¿ĺåı¯ä»¥
    -0.10
    åŁĤ
    -0.10
    opensource
    -0.10
    èĥ¸åīį
    -0.09
    室åıĭ
    -0.09
    ç¼Ł
    -0.09
    ä½Ĩä¹Ł
    -0.09
    åĽłä¸ºä»ĸ们
    -0.09
    ouble
    -0.09
    åĽłä¸ºæĪij
    -0.09
    POSITIVE LOGITS
    ä»Ģä¹Īåij¢
    0.10
    亲çĪ±çļĦ
    0.09
    fter
    0.09
    ä¸Ģè¾¹
    0.09
    å°±æľīäºĨ
    0.09
    lle
    0.08
    oner
    0.08
    ä¸Ģæĸ¹éĿ¢æĺ¯
    0.08
    ame
    0.08
    åĸ½
    0.08
    Activations Density 0.312%

    No Known Activations