© 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. 23946
    Prev
    Next
    INDEX
    Explanations

    delta, noise, correlated disorder

    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
    ured
    -0.08
    _quota
    -0.07
    çıŃçīĻ
    -0.07
    éĥ¨å°±
    -0.07
    å±ĪæĮĩ
    -0.07
    isans
    -0.07
     Routes
    -0.07
    reature
    -0.07
    è¡Ģèī²
    -0.07
    urally
    -0.06
    POSITIVE LOGITS
    ength
    0.08
    illi
    0.08
    chet
    0.08
    èŁĢ
    0.07
    pike
    0.07
    èIJ½å®ŀ好
    0.07
    ä¼ģä¸ļ家
    0.07
    phin
    0.06
     getRequest
    0.06
     infinit
    0.06
    Activations Density 0.002%

    No Known Activations