© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 12245
    Prev
    Next
    INDEX
    Explanations

    Simpson names

    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
    Negative Logits
    ingly
    -0.11
    -0.10
    -important
    -0.09
    ìĤ¬íķŃ
    -0.08
    itz
    -0.08
    ABILITY
    -0.08
    uti
    -0.08
    åıijå±ķæĸ¹åIJij
    -0.08
    iness
    -0.08
    æ°¨éħ¸
    -0.08
    POSITIVE LOGITS
    -minded
    0.10
    ä¸įäºĨ
    0.09
    iated
    0.09
    /qu
    0.09
    eded
    0.09
    sey
    0.09
    firm
    0.09
    lox
    0.08
    ä¼ĹæīĢ
    0.08
    ry
    0.08
    Activations Density 0.004%

    No Known Activations