© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36267
    Prev
    Next
    INDEX
    Explanations

    toll booth or toll road

    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
    è·Į
    -0.11
    ç¾İå¦Ļ
    -0.11
    нев
    -0.10
    bral
    -0.10
    ä½ĵèĤ²å½©ç¥¨
    -0.09
    åī§æľ¬
    -0.09
    彩票
    -0.09
    ÑĢоÑģÑģ
    -0.09
    _gc
    -0.09
    åºŁå¼ĥ
    -0.09
    POSITIVE LOGITS
    ichel
    0.10
     toll
    0.09
    ç¼´è´¹
    0.09
    æĶ¶è´¹ç«Ļ
    0.09
    è¿IJèIJ¥
    0.09
     Cyril
    0.08
    edes
    0.08
    æŃ£éĿ¢
    0.08
     BST
    0.08
    åħį
    0.08
    Activations Density 0.020%

    No Known Activations