© 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. 48663
    Prev
    Next
    INDEX
    Explanations

    reflexive pronouns and oneself

    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
    éļıæŶéļıåľ°
    -0.09
    åĽ½åĨħå¤ĸ
    -0.08
     swings
    -0.08
    æįħ
    -0.08
    å®ŀå®ŀåľ¨åľ¨
    -0.08
     миÑĢов
    -0.08
    æĻ®éĢļçļĦ
    -0.08
    ä¸Ģå®ļçļĦ
    -0.08
    ade
    -0.08
    ضة
    -0.08
    POSITIVE LOGITS
     ourselves
    0.18
     yourself
    0.18
     ÑģебÑı
    0.18
     oneself
    0.17
     Ñģебе
    0.17
     himself
    0.16
     herself
    0.16
     myself
    0.15
     themselves
    0.15
    èĩªå·±
    0.15
    Activations Density 0.048%

    No Known Activations