© 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. 15330
    Prev
    Next
    INDEX
    Explanations

    code syntax markup

    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
    acular
    -0.07
    ç³ĸå°¿çĹħçļĦ
    -0.06
    ooth
    -0.06
    örn
    -0.06
    eby
    -0.06
    erness
    -0.06
    @m
    -0.06
    lease
    -0.06
     decltype
    -0.06
    室åĨħå¤ĸ
    -0.06
    POSITIVE LOGITS
     sogenannten
    0.07
    arze
    0.07
    æĸ°å®ī
    0.07
    èıĩ
    0.07
    å¼Ī
    0.07
     sogenannte
    0.07
    tul
    0.06
     appunto
    0.06
    ä»Ģä¹Īåij¢
    0.06
    æĪijåı«
    0.06
    Activations Density 1.126%

    No Known Activations