© 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. 19842
    Prev
    Next
    INDEX
    Explanations

    tens digit of

    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
    orsa
    -0.07
    ikt
    -0.07
    tract
    -0.07
    åIJĮåIJį
    -0.07
    夫妻åħ³ç³»
    -0.07
    à¹Ħว
    -0.06
    æı¡çĿĢ
    -0.06
     Zoo
    -0.06
    ä¸Ĭ课æŶ
    -0.06
    çĬ¹
    -0.06
    POSITIVE LOGITS
    abic
    0.08
    åĪ»éª¨
    0.07
    ãĥ³ãĤ¸
    0.07
    herme
    0.07
    tahl
    0.07
    ersist
    0.07
    _LOGGER
    0.07
    ookies
    0.07
    engl
    0.07
    æĶ¶å°¾
    0.07
    Activations Density 0.002%

    No Known Activations