© 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. 52723
    Prev
    Next
    INDEX
    Explanations

    governor of

    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
    主人
    -0.10
    apesh
    -0.09
    æĶ¹ä¸º
    -0.09
    ä¸Ģ个人
    -0.08
    æĶ¹æĪIJ
    -0.08
    йÑĤе
    -0.08
    éĻ¢éķ¿
    -0.08
    iac
    -0.08
    豨
    -0.08
    theless
    -0.08
    POSITIVE LOGITS
    äºĭåĦ¿
    0.08
    以åħ¶
    0.08
    æľĢå¿«
    0.08
    代表çĿĢ
    0.08
    urator
    0.08
    å¾Īæľīåı¯èĥ½
    0.08
    å¨ĺ家
    0.07
    ÑĮ
    0.07
    ç±½
    0.07
    otre
    0.07
    Activations Density 0.078%

    No Known Activations