© 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. 32369
    Prev
    Next
    INDEX
    Explanations

    online, digital, or electronic services

    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
    -value
    -0.07
    å±Ģåľ°
    -0.06
    angan
    -0.06
     Aé
    -0.06
    æĢ§åĬŁèĥ½
    -0.06
    åĴĮå½±åĵį
    -0.06
    sez
    -0.06
     HuffPost
    -0.06
    _GPU
    -0.06
    ä¹ĭä¸Ģæĺ¯
    -0.06
    POSITIVE LOGITS
    /mobile
    0.11
    -enabled
    0.10
    /web
    0.10
    ä¸İä¼łç»Ł
    0.10
    çīĪçļĦ
    0.10
    /Web
    0.09
    /software
    0.09
    便æį·
    0.09
    åĴĮç½ij绾
    0.09
    å¹³åı°çļĦ
    0.09
    Activations Density 0.364%

    No Known Activations