© 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. 51833
    Prev
    Next
    INDEX
    Explanations

    biological suffixes

    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
    ë¹Ħê°Ģ
    -0.08
    -svg
    -0.07
    lin
    -0.07
     meur
    -0.07
    jte
    -0.06
    æĭł
    -0.06
    åıĺåĮĸæĥħåĨµ
    -0.06
    deo
    -0.06
    åĢ
    -0.06
    åĩĮéľĦ
    -0.06
    POSITIVE LOGITS
    rium
    0.08
    çĭ¬æłijä¸Ģå¸ľ
    0.08
    artos
    0.08
    éŨ类
    0.07
    ÑĥдаÑĢ
    0.07
    ÃŃso
    0.07
    ลัà¸ģษà¸ĵà¹Į
    0.07
    æĿIJ
    0.06
     formally
    0.06
    armac
    0.06
    Activations Density 0.014%

    No Known Activations