© 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. 54012
    Prev
    Next
    INDEX
    Explanations

    intermittent

    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
    nc
    -0.09
    anon
    -0.09
    åĪĿ次
    -0.09
    npos
    -0.09
     memcmp
    -0.08
     SOP
    -0.08
    积æŀģåĵįåºĶ
    -0.08
    æĦı
    -0.08
    æ¼Ĩ
    -0.08
    .GetCurrent
    -0.08
    POSITIVE LOGITS
    ä¸įå®ļ
    0.12
    çĻ«
    0.11
    æŃĩ
    0.11
     intermittent
    0.11
    å±±åİ¿
    0.10
    鼶ç¢İ
    0.10
    éĹ´
    0.10
    çĦ°
    0.09
    æĢ§å¼º
    0.09
    äº¤æĽ¿
    0.09
    Activations Density 0.103%

    No Known Activations