© 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. 23826
    Prev
    Next
    INDEX
    Explanations

    alcohol Drinking

    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
    opsis
    -0.09
     ÐIJпÑĢе
    -0.09
    -0.08
     Ñģно
    -0.08
    åī
    -0.08
    -counter
    -0.08
    à¹ģà¸ŀร
    -0.08
    alous
    -0.08
     ÐľÐµÑħа
    -0.08
    Incre
    -0.08
    POSITIVE LOGITS
    u
    0.07
    à¤łà¥Ģ
    0.07
    ...
    0.07
     ...
    0.07
    es
    0.06
     Flem
    0.06
    ал
    0.06
    èľĴ
    0.06
    å¸ĮæľĽå¯¹æĤ¨
    0.06
    zin
    0.05
    Activations Density 0.005%

    No Known Activations