© 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. 39260
    Prev
    Next
    INDEX
    Explanations

    human beings

    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
    åķ¸
    -0.10
    èĢģ人家
    -0.09
    è´²
    -0.09
    çĴľ
    -0.09
    çĭĴ
    -0.09
    ä¸ĵèģĮ
    -0.09
     pseud
    -0.08
    éĿ¢åIJij
    -0.08
    isos
    -0.08
    ä¸į失
    -0.08
    POSITIVE LOGITS
    å¼±çĤ¹
    0.09
    人类
    0.09
     humans
    0.09
    寿
    0.09
    åģ¶
    0.09
    Poster
    0.09
    æī¹
    0.08
    æĶ¯
    0.08
     whom
    0.08
    åĨĹ
    0.08
    Activations Density 0.092%

    No Known Activations