© 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. 22498
    Prev
    Next
    INDEX
    Explanations

    mathematical powers and sequences

    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
    {text
    -0.08
    uto
    -0.07
    athom
    -0.07
    æĿ¾é¼ł
    -0.07
    件çļĦ
    -0.07
    IndexChanged
    -0.07
    人å±ħ
    -0.07
     Ponti
    -0.06
    ç¾İä¸Ń
    -0.06
    iel
    -0.06
    POSITIVE LOGITS
    çħ§çĽ¸
    0.07
    æľīåĩłä¸ª
    0.07
    bish
    0.07
    lub
    0.06
    unger
    0.06
    -fetch
    0.06
    ADR
    0.06
    otten
    0.06
    _fetch
    0.06
    biot
    0.06
    Activations Density 0.002%

    No Known Activations