© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 58410
    Prev
    Next
    INDEX
    Explanations

    setting parameters or states

    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
    afil
    -0.08
    packed
    -0.08
    nets
    -0.08
    NECT
    -0.07
    anova
    -0.07
    ç¥ŀåħµ
    -0.07
    iores
    -0.07
    æľºçIJĨ
    -0.07
    åĿŀ
    -0.07
    glomer
    -0.07
    POSITIVE LOGITS
     conveniently
    0.08
     conventions
    0.07
    zer
    0.07
     fixing
    0.07
     convenient
    0.07
     Convenient
    0.07
    使ä¹ĭ
    0.07
    鼶çĤ¹
    0.07
    auge
    0.07
    使å¾Ĺ
    0.07
    Activations Density 0.005%

    No Known Activations