© 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. 43312
    Prev
    Next
    INDEX
    Explanations

    degree descriptors

    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
    åIJĪ
    -0.08
    гоÑĢе
    -0.08
    çŁŃçŁŃçļĦ
    -0.07
    pery
    -0.07
    bidden
    -0.07
    ç§ijçļĦ
    -0.07
    tempts
    -0.07
    å®Łãģ«
    -0.07
     Offline
    -0.07
    -kind
    -0.07
    POSITIVE LOGITS
    åĴĮä¸Ń
    0.12
    -medium
    0.11
    åĪ°ä¸Ń
    0.11
    ish
    0.10
    çĽ¸å¯¹èĢĮè¨Ģ
    0.10
     medium
    0.09
    èĩ³æŀģ
    0.09
     جداÙĭ
    0.09
    /mod
    0.09
     relative
    0.08
    Activations Density 0.302%

    No Known Activations