© 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. 62316
    Prev
    Next
    INDEX
    Explanations

    proportional representation

    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
    awan
    -0.07
    ipt
    -0.07
    è¾ľ
    -0.07
    embre
    -0.07
    ysten
    -0.06
    ipto
    -0.06
    æĺ¯å¥½
    -0.06
    åįķä½įåĴĮ
    -0.06
    éĵ¸å°±
    -0.06
     |
    -0.06
    POSITIVE LOGITS
    éĢļè¿ĩåľ¨
    0.16
     via
    0.14
    éĢļè¿ĩå°Ĩ
    0.13
    via
    0.13
     пÑĥÑĤем
    0.12
     poprzez
    0.12
     поÑģÑĢедÑģÑĤвом
    0.12
     tramite
    0.12
    Via
    0.12
     represented
    0.11
    Activations Density 0.304%

    No Known Activations