© 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. 38249
    Prev
    Next
    INDEX
    Explanations

    public:

    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
    ellig
    -0.08
    culares
    -0.08
    ä¸Ģäºĭ
    -0.08
    ÑģмоÑĤÑĢÑı
    -0.07
    dei
    -0.07
    .prepare
    -0.07
    å°¼åı¤
    -0.07
    czyn
    -0.07
     dér
    -0.07
    ült
    -0.07
    POSITIVE LOGITS
    åħ·ä½ĵçļĦ
    0.06
    åijĺ
    0.06
    eram
    0.06
    æĹ¥è¢«
    0.06
    ;
    0.06
    ä¹°ä¹°
    0.06
    åı¯è¨Ģ
    0.06
    æ¤Ĵ
    0.06
    eri
    0.06
    };
    0.06
    Activations Density 0.196%

    No Known Activations