© 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. 62618
    Prev
    Next
    INDEX
    Explanations

    @ package 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
    adol
    -0.08
    /vnd
    -0.07
    untut
    -0.07
    /MPL
    -0.07
    abay
    -0.07
    atrice
    -0.07
    arket
    -0.07
    ifax
    -0.07
    åĵ¡
    -0.07
    èĩªçĶ±èĩªåľ¨
    -0.06
    POSITIVE LOGITS
    oss
    0.07
    Pages
    0.07
    导åĩºæķ°æį®
    0.07
    OMIC
    0.07
    jų
    0.07
    uka
    0.07
    ä¸ī家
    0.07
    /local
    0.07
    sik
    0.06
    ornos
    0.06
    Activations Density 0.030%

    No Known Activations