© 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. 22728
    Prev
    Next
    INDEX
    Explanations

    list punctuation and conjunctions

    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
    å¿Ĵ
    -0.11
    éĹ¹
    -0.10
    ->__
    -0.10
     ipad
    -0.09
    以åıĬåħ¶ä»ĸ
    -0.09
    رÙģ
    -0.09
    å®ĥçļĦ
    -0.09
    鬧
    -0.09
    .ship
    -0.08
    BOT
    -0.08
    POSITIVE LOGITS
    建åĨĽ
    0.08
    ä¸īåĨľ
    0.08
     nt
    0.08
    çĬĢ
    0.08
    è¿ĩçļĦ
    0.08
    fresh
    0.07
    -loader
    0.07
    ãģ©ãģ®
    0.07
     Roch
    0.07
    ajo
    0.07
    Activations Density 0.870%

    No Known Activations