© 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. 34229
    Prev
    Next
    INDEX
    Explanations

    mind and soul

    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
    æ·ĭ
    -0.10
    ạng
    -0.09
    ifest
    -0.09
    ãĤĥ
    -0.09
    èĦļä¸ĭ
    -0.09
    åį¯
    -0.09
    æİĸ
    -0.09
     Moo
    -0.09
    èĮ¨
    -0.08
    妻
    -0.08
    POSITIVE LOGITS
    nim
    0.10
    æľīèĥ½åĬĽ
    0.09
     Westminster
    0.09
    tra
    0.09
    è¿IJä½ľ
    0.09
     capac
    0.09
    аеÑĤÑģÑı
    0.09
    ä¸įåıĹ
    0.08
    èĥ½åĬĽåĴĮ
    0.08
    nable
    0.08
    Activations Density 0.030%

    No Known Activations