© 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. 62971
    Prev
    Next
    INDEX
    Explanations

    experience / staying

    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
    åĻ
    -0.10
    /native
    -0.09
    .EventArgs
    -0.09
    æīĭä¸ĭ
    -0.09
    æ¼ıæ°´
    -0.09
     pard
    -0.08
    åħ¨çIJĥ
    -0.08
    æ±¾
    -0.08
    hya
    -0.08
    æįIJèµł
    -0.08
    POSITIVE LOGITS
    åģľçķĻ
    0.13
    ä½ı宿
    0.13
    第ä¸Ģ天
    0.11
    é¢Ħå®ļ
    0.11
    ä½ıåľ¨
    0.11
    æĶ»çķ¥
    0.11
    å¸ĤåĮº
    0.10
    çŃ¾è¯ģ
    0.10
     staying
    0.10
    游çİ©
    0.10
    Activations Density 0.063%

    No Known Activations