© 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. 53861
    Prev
    Next
    INDEX
    Explanations

    anyone, everybody, or people

    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
    éļĨ
    -0.09
    æĿľåħ°
    -0.09
    ä¸ŃåĽ½åı¤ä»£
    -0.09
    .Options
    -0.08
    emark
    -0.08
    æ¹
    -0.08
    å½ĵçĦ¶
    -0.08
    æij
    -0.08
    ä¹ħ
    -0.08
    гал
    -0.08
    POSITIVE LOGITS
     anyone
    0.19
     everyone
    0.19
    ä»»ä½ķ人
    0.19
     anybody
    0.17
     everybody
    0.17
    人人
    0.17
    å¾Īå¤ļ人éĥ½
    0.17
     Anyone
    0.16
    人éĥ½
    0.16
     people
    0.16
    Activations Density 0.086%

    No Known Activations