© 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. 29805
    Prev
    Next
    INDEX
    Explanations

    competitor cities elsewhere

    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´§æºIJ
    -0.10
    çĻ½é©¬
    -0.09
    æİ¥èijĹ
    -0.09
    fills
    -0.08
    çĤ¹è¯Ħ
    -0.08
    locals
    -0.08
    箸
    -0.08
    eeper
    -0.08
     pred
    -0.08
    imary
    -0.08
    POSITIVE LOGITS
    ç«ŀäºī对æīĭ
    0.13
    åIJĮè¡Į
    0.12
    åħ¶ä»ĸåĽ½å®¶
    0.11
    åĭ¢
    0.11
     competitor
    0.11
    对æłĩ
    0.10
    åIJĮç±»
    0.10
    çļĦåģļæ³ķ
    0.10
    羡æħķ
    0.10
    人家
    0.10
    Activations Density 0.218%

    No Known Activations