© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7854
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun + own

    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
    amac
    -0.10
    iet
    -0.09
    åıijåħī
    -0.09
    ä¸Ģå®ļ
    -0.09
    earing
    -0.09
    IDL
    -0.09
    kul
    -0.09
    verständlich
    -0.08
    atest
    -0.08
    å«©
    -0.08
    POSITIVE LOGITS
     own
    0.22
    èĩªå·±çļĦ
    0.19
    own
    0.16
    _own
    0.16
    èĩªå·±
    0.15
    Own
    0.14
    äºĨèĩªå·±çļĦ
    0.14
     Own
    0.14
    èĩªèº«çļĦ
    0.12
    èĩªèº«
    0.12
    Activations Density 0.080%

    No Known Activations