© 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. 47739
    Prev
    Next
    INDEX
    Explanations

    4096

    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
    人èĥ½
    -0.07
    gles
    -0.07
     INTERRU
    -0.07
    ео
    -0.07
    驻马
    -0.07
    rieved
    -0.07
    åĩºå¸ŃäºĨ
    -0.07
    สมà¸Ħวร
    -0.07
    ohner
    -0.07
    plete
    -0.07
    POSITIVE LOGITS
    iddy
    0.08
    icot
    0.07
    èĢIJå¾·
    0.07
    alus
    0.06
    estre
    0.06
    hd
    0.06
    æİ¥ä¸ĭ
    0.06
    Ń
    0.06
    lace
    0.06
    arth
    0.06
    Activations Density 0.022%

    No Known Activations