© 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. 58946
    Prev
    Next
    INDEX
    Explanations

    possessives followed by nouns or locations

    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
    åĬłåĢį
    -0.09
    /xhtml
    -0.09
    ä¹Łè¶ĬæĿ¥è¶Ĭ
    -0.09
    åĵij
    -0.08
    åĿŀ
    -0.08
    ckt
    -0.08
    èī¯å¿ĥ
    -0.08
    红楼
    -0.08
    ivia
    -0.08
    æ»ĭ
    -0.08
    POSITIVE LOGITS
    åĢĴåľ¨
    0.10
    å¹³æŶ
    0.09
    åĪĿæŃ¥
    0.09
    äºĭåħĪ
    0.09
    éĿĽ
    0.09
    çīĽå¥¶
    0.09
    enne
    0.09
    æѤåīį
    0.09
    äºĭåıij
    0.09
    æĬ¢æķij
    0.09
    Activations Density 0.041%

    No Known Activations