© 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. 39541
    Prev
    Next
    INDEX
    Explanations

    self-referential and reflexive pronouns

    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
    nar
    -0.09
    éªĬ
    -0.09
    itures
    -0.09
    å·¡è§Ĩ
    -0.09
    iture
    -0.09
    åıĥ
    -0.08
    agal
    -0.08
    ogle
    -0.08
    ewhere
    -0.08
    RB
    -0.08
    POSITIVE LOGITS
    /self
    0.11
    (Self
    0.11
    åĮĸåIJĪ
    0.11
    æĬĬèĩªå·±
    0.11
    SELF
    0.10
    åĺ´å·´
    0.09
     СообÑī
    0.09
    å¼¢
    0.09
    çķ´
    0.09
    æķ²
    0.09
    Activations Density 0.064%

    No Known Activations