© 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. 21054
    Prev
    Next
    INDEX
    Explanations

    majority of, trapped in, with flames, come in, increased incidence, the fact, all share, layoffs hit, infinite scroll

    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
    imson
    -0.07
    ؤÙĩا
    -0.07
    èĥ½å¤Łå¯¹
    -0.07
    ooth
    -0.07
    è¯Ľ
    -0.07
    ä¸įå¾Ĺ使çĶ¨
    -0.07
    quares
    -0.07
    duk
    -0.07
    åį´ä¸įèĥ½
    -0.07
    åħ³æ³¨èĢħ
    -0.07
    POSITIVE LOGITS
    вел
    0.07
     oluÅŁ
    0.07
    æĺ¯åĽł
    0.07
    ç»ıè¿ĩå¤ļå¹´çļĦ
    0.07
    fy
    0.07
    åıĪä¸į
    0.06
    æĹ¢æľī
    0.06
    shell
    0.06
     notoriously
    0.06
    åĽł
    0.06
    Activations Density 0.395%

    No Known Activations