© 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. 39536
    Prev
    Next
    INDEX
    Explanations

    aircraft, flight, and aviation

    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
    çIJĨ
    -0.09
    å¼Ģåĩº
    -0.09
    adro
    -0.08
    ullo
    -0.08
    $core
    -0.08
    两åıª
    -0.08
    åħ¬ä¼Ĺåı·
    -0.08
    ä¸ĭæīĭ
    -0.08
    agers
    -0.08
    è¾ŀ
    -0.08
    POSITIVE LOGITS
    翼
    0.09
    éĥ¨åī¯éĥ¨éķ¿
    0.09
    леп
    0.09
    åį§
    0.09
    å¤ĸå½¢
    0.09
    éħįæĸ¹
    0.09
     Goth
    0.09
    çĹĽ
    0.08
    ilder
    0.08
    é«»
    0.08
    Activations Density 0.087%

    No Known Activations