© 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. 61198
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun + own/self

    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
    æĤī
    -0.09
    çīĮ
    -0.09
    HDR
    -0.09
    ertos
    -0.08
     Dund
    -0.08
    ä¸į失
    -0.08
    å·¡åĽŀ
    -0.08
    饫
    -0.08
    æݥ触åĪ°
    -0.08
    æľīéĻIJ
    -0.08
    POSITIVE LOGITS
     alone
    0.16
    alone
    0.16
    à¹Ģà¸Ńà¸ĩ
    0.15
     itself
    0.14
    æľ¬èº«
    0.14
     Alone
    0.13
    çĭ¬èĩª
    0.13
     ìŀIJì²´
    0.13
     themselves
    0.13
     Ñģами
    0.12
    Activations Density 0.036%

    No Known Activations