© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 37428
    Prev
    Next
    INDEX
    Explanations

    problem back diffusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    terr
    -0.07
     Roths
    -0.06
    Lite
    -0.06
     orally
    -0.06
    补缺
    -0.06
    ropa
    -0.06
    ikon
    -0.06
    PRES
    -0.06
    interval
    -0.06
    çļ®èĤ¤çĹħ
    -0.06
    POSITIVE LOGITS
    åļı
    0.09
    æħ
    0.08
    æ®Ĩ
    0.07
     particol
    0.07
    èį¡
    0.07
    åijľåijľ
    0.07
    åĴĮå¯Ĩçłģ
    0.07
     Äijâu
    0.07
     règlement
    0.07
    idar
    0.07
    Activations Density 0.014%

    No Known Activations