© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9027
    Prev
    Next
    INDEX
    Explanations

    educational, research, or reference purposes

    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
    avis
    -0.09
     eins
    -0.08
    oking
    -0.08
    SM
    -0.08
    oka
    -0.08
    _SM
    -0.08
    asty
    -0.08
    å¼ĤæĢ§
    -0.08
    çĽ¸å¯¹äºİ
    -0.08
    ç«ĭ马
    -0.08
    POSITIVE LOGITS
    çľĭä½ł
    0.09
    æĶ¶èĹı
    0.09
    æĶ»åĬ¿
    0.09
    æľīå¾ħ
    0.09
    æѦè£ħ
    0.09
    èħIJ
    0.08
    poon
    0.08
     nett
    0.08
    çĹķ
    0.08
    ä¸įå¾Ĺ转载
    0.08
    Activations Density 0.015%

    No Known Activations