© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53119
    Prev
    Next
    INDEX
    Explanations

    action occurring

    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¸Ģå¥Ĺ
    -0.10
    ä¸Ģçľĭ
    -0.09
    Factors
    -0.09
    åħĭåĪ¶
    -0.09
    è´£ç¼ĸ
    -0.08
    atk
    -0.08
    Mutable
    -0.08
    LESS
    -0.08
    ä¿Ŀä½ı
    -0.08
    .permission
    -0.08
    POSITIVE LOGITS
     action
    0.12
    çĥŃéĹ¹
    0.12
    ä¹IJ趣
    0.11
    åĬ¨ä½ľ
    0.11
     excitement
    0.10
    ono
    0.10
    -action
    0.10
    è¡ĮåĬ¨
    0.09
    丰å¯Į
    0.09
    çĦ¦çĤ¹
    0.09
    Activations Density 0.101%

    No Known Activations