© 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. 57348
    Prev
    Next
    INDEX
    Explanations

    opened fire or opened up

    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
     Beard
    -0.09
     Newton
    -0.09
    ê·¹
    -0.09
    è¿Ļç§įæĥħåĨµ
    -0.08
    chet
    -0.08
    iless
    -0.08
    skins
    -0.08
     اÙĦÙħدÙĨÙĬ
    -0.08
    çĹĩçĬ¶
    -0.08
    é«ĺä½į
    -0.08
    POSITIVE LOGITS
    èĮŃ
    0.09
    çĽħ
    0.09
    çīĩåŃIJ
    0.09
    è··
    0.09
    flies
    0.09
    幺
    0.09
    ä¸Ģæľ¬ä¹¦
    0.09
    æĦıæĥ³ä¸įåĪ°
    0.09
    ARNING
    0.08
    èĵĭ
    0.08
    Activations Density 0.025%

    No Known Activations