© 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. 55381
    Prev
    Next
    INDEX
    Explanations

    pi

    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
    orado
    -0.08
    tty
    -0.07
    pez
    -0.07
    tav
    -0.07
    åŃ£åIJİ
    -0.07
    ermen
    -0.07
    skraft
    -0.07
    atica
    -0.07
    çĵ®
    -0.07
    &w
    -0.07
    POSITIVE LOGITS
    Ỽm
    0.06
    _helpers
    0.06
    以å¤ĸçļĦ
    0.06
    è¿Ļ个大
    0.06
    arius
    0.06
    lea
    0.06
    ripp
    0.06
    åĨ¤
    0.06
    çīĮ
    0.06
    uo
    0.06
    Activations Density 0.005%

    No Known Activations