© 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. 53903
    Prev
    Next
    INDEX
    Explanations

    public apology for friendship

    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
    mdi
    -0.09
    INV
    -0.09
    çī¹åĪ«
    -0.08
     nhá»Ŀ
    -0.08
     Invent
    -0.08
     McD
    -0.08
    æĹ¶ä»£çļĦ
    -0.08
    è¿Ļä¸ĢåĪ»
    -0.08
    pressive
    -0.08
    è¡¥åģ¿
    -0.08
    POSITIVE LOGITS
    ç¨įç¨į
    0.13
    å±ħçĦ¶
    0.12
    ç¨įå¾®
    0.12
    ç«ŁçĦ¶
    0.11
    ç¨į
    0.11
    ä¸įèĤ¯
    0.11
    åĿļå®ļä¸į
    0.10
     mere
    0.10
     slightest
    0.10
    åĵªæĢķ
    0.10
    Activations Density 0.141%

    No Known Activations