© 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. 49502
    Prev
    Next
    INDEX
    Explanations

    above error

    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
     ës
    -0.07
    Prem
    -0.07
     Prem
    -0.07
    าà¸ĩ
    -0.06
    riere
    -0.06
    æķĪ
    -0.06
    çħ§
    -0.06
    æĿ¥è¯´
    -0.06
     illim
    -0.06
    reifen
    -0.06
    POSITIVE LOGITS
    ound
    0.09
    æīĢ示
    0.07
     wÅĤaÅĽnie
    0.07
    åĤ»
    0.07
    plus
    0.07
    缺ä¸Ģ
    0.07
    ä¸ĩ以ä¸Ĭ
    0.07
    _bal
    0.07
    minus
    0.07
    hz
    0.07
    Activations Density 0.058%

    No Known Activations