© 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. 46367
    Prev
    Next
    INDEX
    Explanations

    conclusion or result

    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
    åĭ¾åĭĴåĩº
    -0.07
    åĭ¾
    -0.06
    orm
    -0.06
    å®°
    -0.06
    åłĨ
    -0.06
    çļĦåħĥç´ł
    -0.06
    PPER
    -0.06
    åĩłä¸ªæĸ¹éĿ¢
    -0.06
    大çĹħ
    -0.06
    为äºĨ使
    -0.06
    POSITIVE LOGITS
     thái
    0.10
     verdict
    0.09
     status
    0.08
     stance
    0.08
    -status
    0.08
    status
    0.08
    .setStatus
    0.08
    æĢģ度
    0.08
    æĢģ
    0.08
    Blank
    0.08
    Activations Density 0.061%

    No Known Activations