© 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. 995
    Prev
    Next
    INDEX
    Explanations

    conspiracy, accomplices, fixing, involvement

    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
    intr
    -0.11
    .appspot
    -0.10
     twe
    -0.10
    对æĸ¹
    -0.09
     Legion
    -0.09
     intr
    -0.09
    éģĴ
    -0.09
    è¿ĺä¸įæĺ¯
    -0.09
    ç«ĭä½ĵ
    -0.09
    VILLE
    -0.08
    POSITIVE LOGITS
    严å¯Ĩ
    0.09
    ä¸įæĿ¥
    0.09
    èį·
    0.09
     together
    0.09
    é»ĺå¥ij
    0.09
    åºij
    0.08
    ality
    0.08
    æĸ¯åŁº
    0.08
    erness
    0.08
    ç»Ħç»ĩå®ŀæĸ½
    0.08
    Activations Density 0.028%

    No Known Activations