© 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. 47217
    Prev
    Next
    INDEX
    Explanations

    age and variables

    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
    污æŁĵçݯå¢ĥ
    -0.07
    ä¸įç»Ŀ
    -0.07
    è¿ĻäºĽåľ°æĸ¹
    -0.07
    ount
    -0.07
     embarrass
    -0.07
    ankan
    -0.07
    NAL
    -0.06
    thanks
    -0.06
    Side
    -0.06
    apore
    -0.06
    POSITIVE LOGITS
     variables
    0.11
    åıĺéĩı
    0.10
    æĺ¯å½±åĵį
    0.10
     predictors
    0.09
    Variables
    0.09
    åıĺéĩıçļĦ
    0.09
     Variables
    0.09
    variables
    0.09
     correlates
    0.09
     correlated
    0.08
    Activations Density 0.141%

    No Known Activations