© 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. 56652
    Prev
    Next
    INDEX
    Explanations

    code section separators

    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
    aos
    -0.09
    ÎŁÎ£
    -0.08
    æĥ³äºĨ
    -0.08
    ahal
    -0.08
    åĪĨ享åĪ°
    -0.07
    WindowState
    -0.07
    ensore
    -0.07
    itats
    -0.07
    acias
    -0.07
    etica
    -0.07
    POSITIVE LOGITS
    åĬĽåĴĮ
    0.07
    ille
    0.06
    奶油
    0.06
    drink
    0.06
    ottom
    0.06
    ä¼ij
    0.06
    ä»Ķ
    0.06
     Crowley
    0.06
    åĬĽ
    0.06
    åĢĴ
    0.06
    Activations Density 0.393%

    No Known Activations