© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14844
    Prev
    Next
    INDEX
    Explanations

    code definitions

    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
    åľ¨å²Ĺ
    -0.07
    annon
    -0.07
    ä½Ĩå®ŀéĻħä¸Ĭ
    -0.07
    è¢ħè¢ħ
    -0.06
    à¹īà¸Ńà¸ĩ
    -0.06
    landes
    -0.06
    isel
    -0.06
    åĪĺ强
    -0.06
    awai
    -0.06
    ç¾²
    -0.06
    POSITIVE LOGITS
    ãĤīãģĦ
    0.08
     anyway
    0.07
    ä¸Ģå¦ĤæĹ¢å¾Ģ
    0.07
    ä¸į误
    0.07
    ál
    0.07
    ä»Ģä¹Īéĥ½ä¸į
    0.07
     anyways
    0.07
     gewoon
    0.07
    Registrar
    0.07
    Token
    0.07
    Activations Density 0.054%

    No Known Activations