© 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. 4798
    Prev
    Next
    INDEX
    Explanations

    actions and deeds

    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
    å¾Ī好
    -0.09
    æ®Ĵ
    -0.09
    æħ¢
    -0.08
    hire
    -0.08
    å¢ŀéķ¿
    -0.08
    âĩ§
    -0.08
    çħŀ
    -0.08
    èİĺ
    -0.08
    yield
    -0.08
    é¦ĸå¸Ń
    -0.08
    POSITIVE LOGITS
     actions
    0.22
    è¡ĮåĬ¨
    0.21
     action
    0.19
    actions
    0.17
    åĬ¨ä½ľ
    0.17
    è¡Įåĭķ
    0.17
    .actions
    0.17
     ACTIONS
    0.17
     Actions
    0.16
    (actions
    0.16
    Activations Density 0.073%

    No Known Activations