© 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. 25062
    Prev
    Next
    INDEX
    Explanations

    reproducibility and repetition

    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
    Not in Any Lists

    No Comments

    Negative Logits
    管çIJĨéĥ¨
    -0.09
     oppos
    -0.08
    éĩı身
    -0.07
    avion
    -0.07
    atego
    -0.07
    TECTION
    -0.07
     Protective
    -0.07
     dynamically
    -0.07
    æĿĤ
    -0.07
    toi
    -0.07
    POSITIVE LOGITS
    åĨįçı¾
    0.11
     standardized
    0.10
    æłĩåĩĨåĮĸçļĦ
    0.10
    æłĩåĩĨåĮĸ
    0.10
     Across
    0.09
    åĨįçİ°
    0.09
     across
    0.09
     reproduc
    0.09
     воÑģпÑĢоиз
    0.09
    éĩįçİ°
    0.09
    Activations Density 0.062%

    No Known Activations