© 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. 56088
    Prev
    Next
    INDEX
    Explanations

    numbers, brackets, and url delimiters

    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
    yton
    -0.09
    thon
    -0.08
    tees
    -0.08
    oser
    -0.08
    æ¹¾
    -0.07
    yed
    -0.06
    yper
    -0.06
    èĮģ
    -0.06
    YRO
    -0.06
     Sâm
    -0.06
    POSITIVE LOGITS
    翼翼
    0.08
    éĥ½ä¸įè¦ģ
    0.08
    	where
    0.08
    $where
    0.07
    åħ¶ä¸Ń
    0.07
     where
    0.07
    ixin
    0.07
     lÆ°u
    0.07
    ammer
    0.07
    Ñģел
    0.07
    Activations Density 0.154%

    No Known Activations