© 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. 56713
    Prev
    Next
    INDEX
    Explanations

    reference spectrum, predetermined track, last noon, reference point, base axis

    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
     procur
    -0.08
     lean
    -0.07
    obb
    -0.07
    åĴĮåľ°æĸ¹
    -0.07
    人åij½
    -0.07
    管çIJĨæĿ¡ä¾ĭ
    -0.07
    à¸Ľà¸£à¸°
    -0.07
     anon
    -0.06
    ensus
    -0.06
    ặn
    -0.06
    POSITIVE LOGITS
    åŁºåĩĨ
    0.09
     reference
    0.08
    reference
    0.08
    åıĤèĢĥ
    0.08
    enchmark
    0.08
    ุà¸ĩ
    0.08
    aton
    0.08
    éĶļ
    0.07
    åıĤçħ§
    0.07
    otime
    0.07
    Activations Density 0.004%

    No Known Activations