© 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. 8747
    Prev
    Next
    INDEX
    Explanations

    jptm

    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
    åĨµ
    -0.07
    oop
    -0.07
    ãģ«ãģĤ
    -0.07
     č↵ č↵
    -0.07
    à¸Ĭัà¸ļ
    -0.07
    aup
    -0.06
    gangs
    -0.06
    urses
    -0.06
    åıijå±ķæ½ľåĬĽ
    -0.06
    onique
    -0.06
    POSITIVE LOGITS
     candid
    0.07
    æŃ¦ä¾¯
    0.07
    akit
    0.07
    å¸Ĥä¸Ń
    0.06
    ÑĢик
    0.06
    ä¼IJ
    0.06
    ÏĨάλ
    0.06
    èĢģå©Ĩ
    0.06
    osso
    0.06
    à¹Ģà¸ķà¸Ńรà¹Į
    0.06
    Activations Density 0.257%

    No Known Activations