© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61894
    Prev
    Next
    INDEX
    Explanations

    class .elements

    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
    åıĪä¸įæĺ¯
    -0.07
    itu
    -0.07
    æĤŁ
    -0.07
    æĴ©
    -0.06
    stö
    -0.06
     HACK
    -0.06
     Hack
    -0.06
     Comp
    -0.06
     comp
    -0.06
    æĴij
    -0.06
    POSITIVE LOGITS
    imenti
    0.08
    é¹ĥ
    0.08
     Rosenstein
    0.08
     Rosenberg
    0.08
    igel
    0.07
    åĪĨä¹ĭ
    0.07
    å¡ŀå°Ķ
    0.07
    æĸ°ç¤¾
    0.07
    pedia
    0.07
    ancar
    0.07
    Activations Density 0.101%

    No Known Activations