© 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. 61336
    Prev
    Next
    INDEX
    Explanations

    amine-functionalized groups

    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
     divis
    -0.08
    irro
    -0.07
    bris
    -0.07
    ÃįS
    -0.06
    rito
    -0.06
    oho
    -0.06
    icule
    -0.06
     TypeName
    -0.06
     Discipl
    -0.06
     taller
    -0.06
    POSITIVE LOGITS
    -rich
    0.10
    丰å¯ĮçļĦ
    0.09
    åĪĨå¸ĥåľ¨
    0.08
    æ±ĩ
    0.08
     activated
    0.07
     sites
    0.07
    _near
    0.07
    éļıå¤Ħåı¯è§ģ
    0.07
    yclic
    0.07
    доб
    0.07
    Activations Density 0.075%

    No Known Activations