© 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. 37954
    Prev
    Next
    INDEX
    Explanations

    configure, state, proxy

    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
    nitz
    -0.08
    anas
    -0.07
    alian
    -0.07
    ihat
    -0.07
    åĽ½åĨħçļĦ
    -0.07
    еÑĩа
    -0.07
    ä¸ĺ
    -0.06
    icara
    -0.06
    ?type
    -0.06
    èĵ
    -0.06
    POSITIVE LOGITS
    è®¾ç½®åľ¨
    0.07
    åĪĨéħįåĪ°
    0.07
    æĥ³å¾Ĺ
    0.07
    æĥ³è¦ģåľ¨
    0.07
    åıijè¡¨åľ¨
    0.07
    ebo
    0.06
    adden
    0.06
    laÅŁ
    0.06
    GMT
    0.06
    dy
    0.06
    Activations Density 0.280%

    No Known Activations