© 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. 60712
    Prev
    Next
    INDEX
    Explanations

    cost of steps or points

    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
    æĪĺæ³ķ
    -0.07
    _userid
    -0.07
    %B
    -0.07
    ansfer
    -0.07
    adena
    -0.07
    æĶ¾å¿ĥ
    -0.07
    åĩīå±±
    -0.07
    èIJ½èĬ±
    -0.07
     Cad
    -0.07
    пода
    -0.07
    POSITIVE LOGITS
    ucas
    0.07
    ongen
    0.07
    åĴĮæĶ¿æ²»
    0.07
    endes
    0.06
    åĴĮè¦ģæ±Ĥ
    0.06
    ä¸İæݧåĪ¶
    0.06
    åIJĦè¡Į
    0.06
    è£ħä¸Ĭ
    0.06
    ÄĤN
    0.06
    edir
    0.06
    Activations Density 0.011%

    No Known Activations