© 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. 62238
    Prev
    Next
    INDEX
    Explanations

    hyphenated words and acronyms

    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
    æĪĸéĢļè¿ĩ
    -0.07
    .opend
    -0.07
    æĪĸ使çĶ¨
    -0.07
    æĪĸå°ij
    -0.07
    ega
    -0.06
    essant
    -0.06
    ulton
    -0.06
    çī¹æ®ĬæĥħåĨµ
    -0.06
    atham
    -0.06
    inet
    -0.06
    POSITIVE LOGITS
    å¤§ä½ľ
    0.08
    æĺ¯ä»Ģä¹ĪæĦıæĢĿ
    0.08
    士æŀĹ
    0.07
    ä»Ģä¹ĪæĦıæĢĿ
    0.07
    åĬłè½½ä¸Ń
    0.07
    IKA
    0.07
    uju
    0.07
    aN
    0.06
    çļĦæĦıæĢĿ
    0.06
     Empleo
    0.06
    Activations Density 0.009%

    No Known Activations