© 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. 60302
    Prev
    Next
    INDEX
    Explanations

    find / out / ify / alphabet

    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
    stime
    -0.09
    jach
    -0.08
    åħ¼æĢ»ç»ıçIJĨ
    -0.08
    stell
    -0.08
    ÏģεÏį
    -0.07
    UserCode
    -0.07
    广éĺĶ
    -0.07
    -separated
    -0.07
    大é¢ĺ
    -0.07
    æ·Ģ
    -0.07
    POSITIVE LOGITS
     spoÅĽród
    0.07
    alise
    0.06
     ÑģиÑģÑĤ
    0.06
    strup
    0.06
    awah
    0.06
     Mojo
    0.06
    ål
    0.06
     muka
    0.06
    mary
    0.06
     differences
    0.06
    Activations Density 0.002%

    No Known Activations