© 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. 64611
    Prev
    Next
    INDEX
    Explanations

    language and code

    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
    ��
    -0.09
     �
    -0.08
    <|im_start|>
    -0.08
     č↵
    -0.07
    �
    -0.07
    ���
    -0.06
    éĴ¦
    -0.06
    pects
    -0.06
    æ¢ħæŀĹ
    -0.06
    ä¸ĺ
    -0.06
    POSITIVE LOGITS
    éph
    0.08
    émon
    0.07
    缸è¾ħ缸æĪIJ
    0.07
    ارة
    0.07
    yme
    0.07
    elp
    0.07
    NameValuePair
    0.07
    çļĦåĩĨå¤ĩ
    0.07
    åĪĨåĪ«ä»İ
    0.07
    Ymd
    0.07
    Activations Density 0.015%

    No Known Activations