© 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. 21096
    Prev
    Next
    INDEX
    Explanations

    capacity, growing, create, member, improve, monter, links

    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
    aura
    -0.07
    ildo
    -0.07
    )._
    -0.06
    åį
    -0.06
    ingham
    -0.06
    gua
    -0.06
    å½ĵ羣
    -0.06
    èĢ½
    -0.06
    å½ĵä¹ĭ
    -0.06
    reja
    -0.06
    POSITIVE LOGITS
    æĮīçħ§åĽ½å®¶
    0.09
    åĬ¨åĬĽæĸ¹éĿ¢
    0.08
    çī¹èģĺ
    0.07
    Rép
    0.07
    bage
    0.07
    llib
    0.07
    eda
    0.07
    éis
    0.07
     Gale
    0.07
    /close
    0.07
    Activations Density 0.039%

    No Known Activations