© 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. 40113
    Prev
    Next
    INDEX
    Explanations

    Woolworth Company or Spencer

    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
    WithName
    -0.10
     arrang
    -0.10
    çī¢åĽºæłijç«ĭ
    -0.09
    éĩĩæļĸ
    -0.09
    åĢ¡
    -0.09
     Sunder
    -0.09
    æĹłå£°
    -0.09
    è¾¾æłĩ
    -0.09
    ä¸ĵåįĸ
    -0.09
    LOAT
    -0.08
    POSITIVE LOGITS
     Accent
    0.08
    orde
    0.08
    exc
    0.08
     Lisbon
    0.08
    Accent
    0.08
     Radar
    0.08
    Gear
    0.08
    ëĵĿ
    0.08
    DR
    0.08
     lÆ°Æ¡ng
    0.08
    Activations Density 0.001%

    No Known Activations