© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 33131
    Prev
    Next
    INDEX
    Explanations

    invoking class or paying bidder

    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
    alang
    -0.07
    ürt
    -0.07
    онÑĭ
    -0.07
    åıĪå¦Ĥä½ķ
    -0.07
    pris
    -0.07
    以èĩ³
    -0.07
    åħ¸åŀĭ
    -0.07
    oho
    -0.07
    alow
    -0.06
     Ost
    -0.06
    POSITIVE LOGITS
    èĢĮä¸įæĺ¯
    0.10
     rather
    0.10
    æīĢåľ¨åľ°
    0.10
     plutôt
    0.09
    æīĢåľ¨
    0.09
     whichever
    0.09
    å®ŀéĻħåĩºåıij
    0.09
    èĢĮéĿŀ
    0.08
    æīĢåľ¨çļĦ
    0.08
    rather
    0.08
    Activations Density 0.109%

    No Known Activations