© 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. 28521
    Prev
    Next
    INDEX
    Explanations

    MC-4 receptor agonists

    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
    AuthProvider
    -0.07
    beck
    -0.07
    âĢİ
    -0.06
    emaine
    -0.06
    ,
    -0.06
    endre
    -0.05
    _tC
    -0.05
    ichick
    -0.05
     cellspacing
    -0.05
    å³Ļ
    -0.05
    POSITIVE LOGITS
    er
    0.11
    ITIES
    0.11
    à¥įह
    0.10
    erce
    0.10
    ities
    0.09
    ê¹IJ
    0.09
    ités
    0.08
    itates
    0.08
    iras
    0.08
    Å¡ten
    0.08
    Activations Density 0.038%

    No Known Activations