© 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. 61168
    Prev
    Next
    INDEX
    Explanations

    object IDs and codes

    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
    jú
    -0.08
    ilk
    -0.07
    å±±ä¹ĭ
    -0.07
    yen
    -0.07
    å®ĥ为
    -0.07
    à°¤à±ģ
    -0.07
    recht
    -0.07
    annel
    -0.07
    framework
    -0.07
    ammad
    -0.07
    POSITIVE LOGITS
    大é£İ
    0.07
     Rosenberg
    0.07
    éĩĮåħĭ
    0.06
    iem
    0.06
    iales
    0.06
    erner
    0.06
    è§Ĩé¢ijä¸Ń
    0.06
    uhr
    0.06
    åįĥåı¤
    0.06
    ayos
    0.06
    Activations Density 0.073%

    No Known Activations