© 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. 39400
    Prev
    Next
    INDEX
    Explanations

    airports, aircraft, and flying

    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
    èµ·é£ŀ
    -0.10
     ави
    -0.10
    âľĪ
    -0.09
    ç¿ħ
    -0.09
    å¸Ń
    -0.09
    æ°ijèĪª
    -0.09
    ç¿ħèĨĢ
    -0.09
    èľ»
    -0.09
     zab
    -0.09
    严èĤĥ
    -0.09
    POSITIVE LOGITS
    ÑĪка
    0.10
     Lans
    0.09
    麻
    0.08
    çªģ
    0.08
    Mis
    0.08
    磫
    0.08
    çĵ¶åŃIJ
    0.08
    æĪĺåĽ½
    0.08
    åĹŁ
    0.08
    icode
    0.08
    Activations Density 0.087%

    No Known Activations