© 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. 31052
    Prev
    Next
    INDEX
    Explanations

    directions and regions

    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
    uerta
    -0.08
    æĺ¯èĥ½
    -0.08
    æ¡Ī件éĢĤçĶ¨æ³ķå¾ĭ
    -0.08
    Defaults
    -0.07
    æ¯Ķ以åīį
    -0.07
    æ¯Ķ以å¾Ģ
    -0.07
     petró
    -0.07
    主åĬŀ
    -0.07
    yek
    -0.07
    bose
    -0.07
    POSITIVE LOGITS
     segment
    0.07
    纯
    0.07
     pure
    0.07
     ÙħØŃÙĪر
    0.07
    èĤĮ
    0.06
     Segment
    0.06
    缴åĪ°
    0.06
     isol
    0.06
     east
    0.06
     tro
    0.06
    Activations Density 0.002%

    No Known Activations