© 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. 27691
    Prev
    Next
    INDEX
    Explanations

    file paths and code components

    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
    uha
    -0.07
    cala
    -0.07
    unek
    -0.07
    /logs
    -0.06
    sWith
    -0.06
    inei
    -0.06
    ×Ļ׾×ķ
    -0.06
    åŁ¹èĤ²åĴĮ
    -0.06
     hypoth
    -0.06
    è·»
    -0.06
    POSITIVE LOGITS
    åIJĬ
    0.08
    常人
    0.07
    /*.
    0.07
    à¹Ħà¸Ł
    0.07
    cust
    0.07
    partials
    0.07
    稽
    0.07
    -search
    0.07
    èįĴåĶIJ
    0.06
    figures
    0.06
    Activations Density 0.251%

    No Known Activations