© 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. 2177
    Prev
    Next
    INDEX
    Explanations

    frequency, age, time, length, range

    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
    æľŁæ»¡åIJİ
    -0.07
    ibd
    -0.07
    éĩľ
    -0.07
    liner
    -0.07
    çļĦä¸Ģ线
    -0.07
    /cop
    -0.07
    vestig
    -0.07
    ynes
    -0.07
    etlen
    -0.07
    ÑģÑĤÑĢе
    -0.07
    POSITIVE LOGITS
    ondon
    0.08
     waarop
    0.07
    èĮĥåĽ´åĴĮ
    0.07
     range
    0.07
    èĮĥåĽ´
    0.07
    åĴĮæŶéĹ´
    0.07
    åĴĮæĸ¹æ³ķ
    0.06
    ä»Ģä¹Īäºĭ
    0.06
    Range
    0.06
    ä½ķåħ¶
    0.06
    Activations Density 0.085%

    No Known Activations