© 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. 22813
    Prev
    Next
    INDEX
    Explanations

    your/my/his + possession

    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
    ungs
    -0.10
    izer
    -0.09
    å¾Īé«ĺçļĦ
    -0.09
    å¾Ī大çļĦ
    -0.09
    pecific
    -0.09
    .slim
    -0.09
    igs
    -0.09
    ä¸ĭçļĦ
    -0.08
    èĭŁ
    -0.08
    ä¸į让
    -0.08
    POSITIVE LOGITS
    ä¿
    0.10
    亲å±ŀ
    0.10
    enheim
    0.09
    社交
    0.09
    åħ¶ä»ĸçļĦ
    0.09
    亲人
    0.09
     Plat
    0.09
    åħ¬åħ±åľºæīĢ
    0.09
    æ¯ĽåŃĶ
    0.09
     ÑĢож
    0.08
    Activations Density 0.019%

    No Known Activations