© 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. 5986
    Prev
    Next
    INDEX
    Explanations

    -ologic, -actic, -ographic suffixes

    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
    داد
    -0.10
    æīĭä¸ŃçļĦ
    -0.10
    pository
    -0.10
    ร
    -0.09
    ight
    -0.09
    pec
    -0.09
    pee
    -0.09
    geist
    -0.09
    ayout
    -0.09
    aq
    -0.09
    POSITIVE LOGITS
    ALLY
    0.25
    ally
    0.21
    -minded
    0.16
    ity
    0.14
    amente
    0.13
    keiten
    0.13
    ITY
    0.12
     minded
    0.12
    ulous
    0.12
    ycl
    0.12
    Activations Density 0.499%

    No Known Activations