© 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. 34481
    Prev
    Next
    INDEX
    Explanations

    school or organizational leaders

    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
    åħį
    -0.09
    æĻ´
    -0.09
     Prescott
    -0.09
    idel
    -0.09
    åĩŃ
    -0.09
    ç»Ŀ
    -0.08
    acam
    -0.08
    abel
    -0.08
    rell
    -0.08
    éĺī
    -0.08
    POSITIVE LOGITS
    æѤç§į
    0.10
    ÑĨеп
    0.10
    rawn
    0.10
    spy
    0.10
    æĦŁçŁ¥
    0.09
    çŁŃæľŁ
    0.09
    istrator
    0.09
    áln
    0.09
    ç»Ĩå¾®
    0.09
     Enums
    0.09
    Activations Density 0.014%

    No Known Activations