© 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. 17366
    Prev
    Next
    INDEX
    Explanations

    numbers and rounding

    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
    ÑģÑı
    -0.07
    wy
    -0.07
    ä¸īå°º
    -0.06
    tables
    -0.06
    å¾Ĺå¾Ī
    -0.06
     tables
    -0.06
    DL
    -0.06
    αι
    -0.06
    edException
    -0.06
    سÙĬر
    -0.06
    POSITIVE LOGITS
    çķĶ
    0.09
    ìĿ´ì¦Ī
    0.08
    zzi
    0.08
    dej
    0.08
    ahoo
    0.08
    uwe
    0.08
    uia
    0.08
    psilon
    0.08
    ¿
    0.08
    fdb
    0.08
    Activations Density 0.035%

    No Known Activations