© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 3065
    Prev
    Next
    INDEX
    Explanations

    possessive 's or plural s

    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
    ivol
    -0.10
    å°ıåŀĭ
    -0.10
    æĿ³
    -0.09
    好çļĦ
    -0.09
    è¾¾åĪ°äºĨ
    -0.09
    .Dom
    -0.09
     Slash
    -0.09
    è¾¾åĪ°
    -0.09
    ä¸ĬéŨ
    -0.09
    енÑĮ
    -0.08
    POSITIVE LOGITS
    们
    0.13
    们çļĦ
    0.13
    åĢij
    0.10
    åĽº
    0.09
    tring
    0.09
    ç¦ıåĪ©
    0.09
     hearts
    0.08
    uess
    0.08
    å¾Ģ
    0.08
    åĮĹæµ·
    0.08
    Activations Density 0.098%

    No Known Activations