© 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. 55520
    Prev
    Next
    INDEX
    Explanations

    following or coming after

    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
    æľ¬æľŁ
    -0.09
    大å®ĹåķĨåĵģ
    -0.09
     вÑĭп
    -0.09
    wendung
    -0.09
    .today
    -0.09
    åĽ½æľīèµĦ产
    -0.09
    æĽ´å¤ļä¿¡æģ¯
    -0.08
    kits
    -0.08
    æĪĺèĥľ
    -0.08
    moid
    -0.08
    POSITIVE LOGITS
    è·Łè¿Ľ
    0.20
     followed
    0.16
    follow
    0.16
    追éļı
    0.14
    éļıä¹ĭ
    0.14
    è·ŁçĿĢ
    0.14
    åħ¶æ¬¡æĺ¯
    0.14
    ç´§æİ¥çĿĢ
    0.14
     follow
    0.13
    æİ¥çĿĢ
    0.13
    Activations Density 0.041%

    No Known Activations