© 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. 57059
    Prev
    Next
    INDEX
    Explanations

    annual events, membership dues

    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
    辫
    -0.09
    é«ĺçŃīéĻ¢æł¡
    -0.09
    çĭİ
    -0.08
    ãģĬ客æ§ĺ
    -0.08
    å½»
    -0.08
    åľ¨çİ°åľº
    -0.08
     thousands
    -0.08
     millions
    -0.08
    å¸ģ
    -0.08
    åIJĮç±»
    -0.08
    POSITIVE LOGITS
    俱ä¹IJéĥ¨
    0.11
    åī¯ä¼ļéķ¿
    0.11
    ç¤¾åĽ¢
    0.10
     membership
    0.10
    ä¼ļåijĺ
    0.10
    membership
    0.10
    ä¸Ģå¦ĤæĹ¢å¾Ģ
    0.10
    è®®é¢ĺ
    0.10
    å¹²äºĭ
    0.10
    åįıä¼ļä¼ļéķ¿
    0.09
    Activations Density 0.134%

    No Known Activations