© 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. 57264
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun followed by noun

    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
    çıı
    -0.10
    æŁ¥çľĭæĽ´å¤ļ
    -0.09
    pill
    -0.09
    ç´§
    -0.09
    积æ·Ģ
    -0.09
    é¹Į
    -0.09
    .synthetic
    -0.09
    _sun
    -0.09
    紧紧
    -0.09
    å®Įæķ´
    -0.09
    POSITIVE LOGITS
    è¡Įä¸ļçļĦ
    0.15
    è¡Įä¸ļåĨħ
    0.14
    è¡Įä¸ļ
    0.13
    è¡Įä¸ļä¸Ń
    0.12
    é¢ĨåŁŁçļĦ
    0.12
    åŀĤ
    0.11
     industry
    0.11
    æīĢåľ¨
    0.11
    é¢ĨåŁŁ
    0.11
    è¡Įä¸ļåıijå±ķ
    0.11
    Activations Density 0.064%

    No Known Activations