© 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. 63793
    Prev
    Next
    INDEX
    Explanations

    album and song titles

    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
    彦
    -0.09
    询
    -0.09
     Mats
    -0.08
    inary
    -0.08
    opers
    -0.08
    /general
    -0.08
    å¹³åĿĩæ¯ı
    -0.08
    åľ°å¤Ħ
    -0.08
    Wis
    -0.08
    >{@
    -0.08
    POSITIVE LOGITS
    èĩªåĪ¶
    0.09
     STRICT
    0.09
    ä»Ģä¹Īä¸ľè¥¿
    0.09
    带åĽŀ
    0.08
    _requires
    0.08
    ç»Ī身
    0.08
    åı®
    0.08
    çī¹è´¨
    0.08
    æĸ°äº§åĵģ
    0.08
    ä¸ļä½Ļ
    0.08
    Activations Density 0.084%

    No Known Activations