© 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. 27629
    Prev
    Next
    INDEX
    Explanations

    in the vicinity of

    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
    é£İåIJ¹è¿ĩ
    -0.08
     use
    -0.07
    å·¥ä½ľä¸İ
    -0.07
    éĢŁåº¦ä¸İ
    -0.07
    åıijå±ķä¸İ
    -0.07
     emphasis
    -0.06
    vey
    -0.06
    ãĤĵãģ³
    -0.06
    use
    -0.06
    çªģå¦Ĥåħ¶æĿ¥çļĦ
    -0.06
    POSITIVE LOGITS
     confines
    0.08
    specified
    0.08
     vicinity
    0.07
    entes
    0.07
    quivo
    0.07
    ENTI
    0.07
    åĪĨå¤ĸ
    0.07
    åIJĪåIJĮæŶ
    0.07
    ä»Ģä¹Īåľ°æĸ¹
    0.07
    å¾ĢæľŁåĽŀ顾
    0.07
    Activations Density 0.210%

    No Known Activations