© 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. 31829
    Prev
    Next
    INDEX
    Explanations

    listing items connected by ,

    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
    imitives
    -0.08
     hopefully
    -0.08
    è¿ĺæľīå°±æĺ¯
    -0.08
    egger
    -0.08
    äºĨä¸Ģå®ļ
    -0.08
     appunto
    -0.08
    stands
    -0.08
    KHTML
    -0.07
    ä¾µ
    -0.07
    åĨįä¸į
    -0.07
    POSITIVE LOGITS
     therefore
    0.08
     dunque
    0.07
    arth
    0.07
    ãģ§ãģĻãģĭãĤī
    0.06
    Ķ
    0.06
    arty
    0.06
    AR
    0.06
    asio
    0.06
    &t
    0.06
    æľīä¸ĭåĪĹ
    0.06
    Activations Density 0.001%

    No Known Activations