© 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. 20193
    Prev
    Next
    INDEX
    Explanations

    lipid and amide compounds

    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
    æ²ĥæĸ¯
    -0.08
    OLVE
    -0.08
    obet
    -0.07
    纶
    -0.07
    èĬ±èĮ¶
    -0.07
    urant
    -0.07
    ONG
    -0.07
    ToStr
    -0.07
    ModelProperty
    -0.07
    à¸ĩ
    -0.07
    POSITIVE LOGITS
    -like
    0.09
    less
    0.07
    çŃīä¼łç»Ł
    0.07
    usual
    0.07
     Trad
    0.07
    ular
    0.07
    unque
    0.07
    çĥĤ
    0.06
    like
    0.06
    æĬ½è±¡
    0.06
    Activations Density 1.308%

    No Known Activations