© 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. 46345
    Prev
    Next
    INDEX
    Explanations

    code snippets and variable names

    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
    en
    -0.07
    åıĺæĢ§
    -0.06
    am
    -0.06
    ass
    -0.06
    ed
    -0.06
    amp
    -0.05
    çªģçĦ¶éĹ´
    -0.05
    st
    -0.05
    A
    -0.05
    imli
    -0.05
    POSITIVE LOGITS
    âĻĢâĻĢ
    0.09
    koch
    0.09
    ë´
    0.09
    ãĢij,ãĢIJ
    0.09
    ª½
    0.09
    esda
    0.09
    kamera
    0.09
    OrElse
    0.09
    grafer
    0.09
     manti
    0.08
    Activations Density 0.063%

    No Known Activations