© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 23138
    Prev
    Next
    INDEX
    Explanations

    end of sentences or exclamations

    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
    Õ¡Õ¯
    -0.07
    asti
    -0.07
    å¹¶ä¸įèĥ½
    -0.07
    潺
    -0.07
    ä½Ĩæĺ¯å¦Ĥæŀľ
    -0.07
    èĽ®
    -0.07
    uck
    -0.07
    èĥľäºİ
    -0.06
    Č
    -0.06
     Ud
    -0.06
    POSITIVE LOGITS
    !]
    0.10
    !**
    0.10
    !'
    0.10
    !»
    0.10
    !\
    0.10
    !
    0.09
    !’
    0.09
    !*
    0.09
    !)
    0.09
    ureka
    0.09
    Activations Density 0.020%

    No Known Activations