© 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. 11184
    Prev
    Next
    INDEX
    Explanations

    constructor arguments

    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
    annah
    -0.08
    bauer
    -0.08
     Navarro
    -0.07
    åĪ®
    -0.07
     cám
    -0.07
    idget
    -0.06
    éĮ
    -0.06
    åºĶå±ĬçĶŁ
    -0.06
    å·¨åħ½
    -0.06
     Gib
    -0.06
    POSITIVE LOGITS
    è®°
    0.09
    åIJį为
    0.08
    æķħåIJį
    0.08
    称ä¹ĭ为
    0.08
    stown
    0.08
     ASSIGN
    0.08
    èµĭåĢ¼
    0.07
    ç®Ģ称
    0.07
    åij½åIJį为
    0.07
    è°ĵä¹ĭ
    0.07
    Activations Density 0.039%

    No Known Activations