© 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. 13859
    Prev
    Next
    INDEX
    Explanations

    phospho-, cyclic, imide, betaine

    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
    å¾Ĺ罪
    -0.08
    -translate
    -0.08
    بÙĬØ©
    -0.08
    ambi
    -0.07
    åľ°éģĵ
    -0.07
    ssen
    -0.06
    ffffff
    -0.06
    segue
    -0.06
     getC
    -0.06
    åľ°éľĩ
    -0.06
    POSITIVE LOGITS
    建æĸ°
    0.07
     ï¼Ī
    0.07
    ounds
    0.07
    æ¼ĵ
    0.07
    hook
    0.07
    incid
    0.07
    åģļèµ·
    0.06
    iese
    0.06
    éģ¥
    0.06
    æ¹ĸéĩĮ
    0.06
    Activations Density 0.006%

    No Known Activations