© 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. 23967
    Prev
    Next
    INDEX
    Explanations

    opposite, inverse, reverse

    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
    ä¸įèµ·
    -0.11
    ä¸įéĻIJ
    -0.10
    bable
    -0.09
    æ»ķ
    -0.09
    ä¸įä¸Ĭ
    -0.09
    ä¸Ĭä¸ĭ
    -0.09
    è°ĥ
    -0.08
    rzy
    -0.08
    rien
    -0.08
    avy
    -0.08
    POSITIVE LOGITS
    缸åıį
    0.13
     opposite
    0.13
    éĢĨ
    0.11
    åıį
    0.11
    .Reverse
    0.11
     reverse
    0.10
     Reverse
    0.10
     пÑĢоÑĤив
    0.10
     Opp
    0.10
    对æĸ¹
    0.10
    Activations Density 0.124%

    No Known Activations