© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22028
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by auxiliary verb

    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
    æĹ¢æľī
    -0.09
    æĹ¢
    -0.09
    éĢĤåIJĪèĩªå·±
    -0.09
    à¸ļ
    -0.09
    ãģ»ãģ©
    -0.08
    dek
    -0.08
     Maurice
    -0.08
    abis
    -0.08
    thus
    -0.08
     Hou
    -0.08
    POSITIVE LOGITS
    ror
    0.10
    称ä¹ĭ
    0.09
     vej
    0.09
    çĿĽ
    0.09
     бонÑĥÑģ
    0.09
    esz
    0.09
    èĨĽ
    0.09
    acles
    0.09
    绫
    0.09
    ignal
    0.09
    Activations Density 0.044%

    No Known Activations