© 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. 18621
    Prev
    Next
    INDEX
    Explanations

    Russian or its entities

    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
    bare
    -0.10
    å°Ħ
    -0.09
     bare
    -0.08
    èłķ
    -0.08
    æIJ¬
    -0.08
    æ²ī积
    -0.08
    ç»ĺåĪ¶
    -0.08
     Bet
    -0.08
    æįŃ
    -0.08
     BET
    -0.08
    POSITIVE LOGITS
    æĹŃ
    0.11
    .ru
    0.10
    æĮ¯åħ´
    0.10
    ÐŁÐµÑĤеÑĢбÑĥÑĢг
    0.10
    æľ¬åľŁ
    0.10
    è¾ĸ
    0.10
    ÑģлÑĥÑĪ
    0.09
    åħĥå®Ŀ
    0.09
    æ¼±
    0.09
    侧
    0.09
    Activations Density 0.111%

    No Known Activations