© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 11030
    Prev
    Next
    INDEX
    Explanations

    hidden, discreet, invisible

    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
    สà¸Ķ
    -0.10
    æ²īé»ĺ
    -0.09
    æIJı
    -0.09
    çļĦç¡®æĺ¯
    -0.09
    ç´§æī£
    -0.09
    çĩ¥
    -0.09
    æĸ°åŁİ
    -0.09
    è¶Ł
    -0.08
    票
    -0.08
    дол
    -0.08
    POSITIVE LOGITS
    ively
    0.10
    æ½ŀ
    0.09
    æĹłå£°
    0.09
    aleb
    0.09
    emente
    0.09
    eways
    0.09
    çľ¼éĩĮ
    0.08
    identally
    0.08
    çĶ°éĩİ
    0.08
    íķĺê²Į
    0.08
    Activations Density 0.015%

    No Known Activations