© 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. 21229
    Prev
    Next
    INDEX
    Explanations

    leading roles and entities

    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
    вам
    -0.08
    令第
    -0.07
    bens
    -0.06
    okok
    -0.06
    èĮ²
    -0.06
    令
    -0.06
     wah
    -0.06
    åħ¹
    -0.05
    çīµè¿ŀ
    -0.05
    çİ°å°Ĩ
    -0.05
    POSITIVE LOGITS
    omt
    0.08
    æĪIJåIJį
    0.08
    !!:
    0.08
    ampen
    0.08
    utre
    0.08
    CHF
    0.07
    $o
    0.07
    emand
    0.07
    ãĤ¿ãĥĥãĥĹ
    0.07
    :`
    0.07
    Activations Density 0.025%

    No Known Activations