© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53137
    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
     pil
    -0.09
    å¡ŀ
    -0.09
     sim
    -0.08
     closure
    -0.08
    _PRIV
    -0.08
    æĭľ
    -0.08
    æ»ŀ
    -0.08
    _typeof
    -0.08
    alis
    -0.08
    ere
    -0.08
    POSITIVE LOGITS
    ä¸ĢçĶŁ
    0.24
     lifetime
    0.21
    ç»Ī身
    0.19
    ç»ĪçĶŁ
    0.19
    Lifetime
    0.19
    ä¸Ģè¾ĪåŃIJ
    0.19
    ä¸Ģä¸ĸ
    0.18
     Lifetime
    0.18
    lifetime
    0.18
    è¿Ļè¾ĪåŃIJ
    0.17
    Activations Density 0.082%

    No Known Activations