© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3048
    Prev
    Next
    INDEX
    Explanations

    possessive ('s) followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    们
    -0.32
    们çļĦ
    -0.28
     herself
    -0.26
    äºĨèĩªå·±çļĦ
    -0.26
    äºĨåIJĹ
    -0.25
     themselves
    -0.24
    们éĥ½
    -0.24
    åIJĮäºĭ们
    -0.24
     fellows
    -0.23
    äºĨåĩł
    -0.23
    POSITIVE LOGITS
    onga
    0.24
    ourney
    0.24
     worth
    0.23
    æĪĸå¤ļ
    0.23
    agina
    0.23
    ÃľN
    0.23
    -eye
    0.22
    æīĢéľĢ
    0.21
    IBLE
    0.21
    _chance
    0.21
    Activations Density 0.027%

    No Known Activations