© 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. 14939
    Prev
    Next
    INDEX
    Explanations

    special characters and code markers

    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
    Aura
    -0.07
    hell
    -0.07
    chor
    -0.07
    alie
    -0.07
    è¯Ń
    -0.06
    ç¬ij
    -0.06
    itt
    -0.06
    èªŀ
    -0.06
    yms
    -0.06
    ÂŃs
    -0.06
    POSITIVE LOGITS
    athers
    0.08
    /close
    0.07
    вий
    0.07
    ahi
    0.07
    ender
    0.07
     سرا
    0.06
    ewis
    0.06
    vecs
    0.06
    ervised
    0.06
    ChangeListener
    0.06
    Activations Density 0.002%

    No Known Activations