© 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. 36647
    Prev
    Next
    INDEX
    Explanations

    buy, use, pick up

    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
    ä¸įæľį
    -0.12
    éĿŀ常好
    -0.11
     luck
    -0.10
    ä¸įçĶĺ
    -0.09
    åĬ±å¿Ĺ
    -0.09
     greed
    -0.09
    ç¾ŀ
    -0.09
    æݪ
    -0.08
    éĿŀ常好çļĦ
    -0.08
    _hi
    -0.08
    POSITIVE LOGITS
    æİıåĩº
    0.10
    ä¸ĢåIJ¬
    0.09
    ILA
    0.09
    à°³
    0.09
    èļģ
    0.09
    _RC
    0.09
    çĶ³è´Ń
    0.09
    æİı
    0.09
    ä¹°åįķ
    0.09
     willingness
    0.09
    Activations Density 0.067%

    No Known Activations