© 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. 18177
    Prev
    Next
    INDEX
    Explanations

    types of, repeats, sorts, users

    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
    _traits
    -0.07
     Gau
    -0.06
    Components
    -0.06
     moment
    -0.06
    æ£ĺ
    -0.06
     downstream
    -0.06
    两份
    -0.06
     Components
    -0.06
    èĬŃ
    -0.06
     gan
    -0.06
    POSITIVE LOGITS
    æŀļ举
    0.09
    cid
    0.09
    ä½ĵåŀĭ
    0.08
    à¸ģารà¸Ħà¹īà¸Ļหา
    0.08
    CID
    0.08
    缴æİ¥æĪĸéĹ´æİ¥
    0.08
    ništ
    0.08
    -ignore
    0.08
    ầm
    0.08
    å¹³åİŁ
    0.07
    Activations Density 0.008%

    No Known Activations