© 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. 47865
    Prev
    Next
    INDEX
    Explanations

    sequence numbers

    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
    euse
    -0.07
    éĤ£åĿĹ
    -0.07
    unique
    -0.07
    .ind
    -0.07
     naz
    -0.06
    RAP
    -0.06
    é¢ĨåħĪæ°´å¹³
    -0.06
    consult
    -0.06
    มà¸Ļ
    -0.06
    nowrap
    -0.06
    POSITIVE LOGITS
    anium
    0.07
    emd
    0.07
    hada
    0.07
     fortf
    0.07
    Reminder
    0.06
    ontan
    0.06
     Ting
    0.06
    éĢ¢
    0.06
    cec
    0.06
    abbo
    0.06
    Activations Density 0.005%

    No Known Activations