© 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. 40417
    Prev
    Next
    INDEX
    Explanations

    wine

    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
    ively
    -0.11
    aneous
    -0.10
    çŃļ
    -0.09
    è¡Įç¨ĭ
    -0.09
    icle
    -0.09
    ional
    -0.09
    å¹³åĿ¦
    -0.09
     Æ¡n
    -0.09
    ions
    -0.09
    毳
    -0.09
    POSITIVE LOGITS
    yard
    0.09
    berger
    0.09
    PILE
    0.09
    quist
    0.08
    åħ¥æĪ·
    0.08
    ep
    0.08
    Ùĥا
    0.08
    å±ij
    0.08
    tru
    0.08
    browser
    0.08
    Activations Density 0.007%

    No Known Activations