© 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. 30656
    Prev
    Next
    INDEX
    Explanations

    game context

    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
    éĶ±
    -0.09
    åī¡
    -0.09
    亲æĪļ
    -0.08
    å¢ŀèµĦ
    -0.08
    omnia
    -0.08
    çĻŀ
    -0.08
    èĥľ
    -0.08
    æ§IJ
    -0.08
    å·²å®ĮæĪIJ
    -0.08
    åĽ¢åľĨ
    -0.08
    POSITIVE LOGITS
    ithe
    0.10
     MAIL
    0.09
    主导
    0.09
     Implements
    0.08
    æľįåĬ¡èĥ½åĬĽ
    0.08
    æĽľ
    0.08
    åĻ¨åħ·
    0.08
    лов
    0.08
    à¹Ģà¸Ĭ
    0.08
    æ¯ħ
    0.08
    Activations Density 0.159%

    No Known Activations