© 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. 31637
    Prev
    Next
    INDEX
    Explanations

    `journal` followed by `ournal` or `pone`

    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
    جاع
    -0.08
    untr
    -0.08
    ivat
    -0.08
    jing
    -0.08
    عÙĦاÙĨ
    -0.07
    jar
    -0.07
    unan
    -0.07
     unmist
    -0.07
    建åħļ
    -0.07
    endant
    -0.07
    POSITIVE LOGITS
    oop
    0.07
    ĮĢ
    0.07
    ez
    0.06
     пÑĢоÑĦи
    0.06
    åıĹçIJĨåIJİ
    0.06
    æĽľæĹ¥
    0.06
    osemite
    0.06
    aqu
    0.06
    inic
    0.06
    ies
    0.06
    Activations Density 0.005%

    No Known Activations