© 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. 18658
    Prev
    Next
    INDEX
    Explanations

    note, mind, warned, realized

    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
     motivo
    -0.06
    éģµå¾ª
    -0.06
    Âł
    -0.06
    å½ĵçĦ¶
    -0.06
    æĪij该
    -0.06
    ×ķ×ķת
    -0.06
    verständ
    -0.06
    ä¸Ģå®ļ
    -0.06
     необÑħодим
    -0.06
    ³³³
    -0.06
    POSITIVE LOGITS
    ä»ĭç»į说
    0.09
    æĺ¯ä¸įåIJĮçļĦ
    0.08
    à¸Ńยูà¹Īà¹Ģสมà¸Ń
    0.08
    é¦ĸæ¬¡åľ¨
    0.08
    __:
    0.07
    Ìģ
    0.07
     Quay
    0.07
    Ùĭ
    0.07
    ocker
    0.07
    XC
    0.07
    Activations Density 0.006%

    No Known Activations