© 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. 12868
    Prev
    Next
    INDEX
    Explanations

    interface projection bundle products control

    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
    å¤
    -0.07
    æ¸ħæ°Ķ
    -0.07
    _indent
    -0.07
    èĦ¾æ°Ķ
    -0.06
    vez
    -0.06
    ìn
    -0.06
    RIA
    -0.06
     MOZ
    -0.06
    ria
    -0.06
    ì¶
    -0.06
    POSITIVE LOGITS
    _impl
    0.08
    ODE
    0.08
     implies
    0.08
    impl
    0.08
    è¦ģè¾¾åĪ°
    0.07
     reverse
    0.07
    Entered
    0.07
    æĹłç¼ĺ
    0.07
    uchy
    0.07
    æıIJ示
    0.07
    Activations Density 0.043%

    No Known Activations