© 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. 8638
    Prev
    Next
    INDEX
    Explanations

    social media, exercise, growth, healing

    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
    plat
    -0.08
    atedral
    -0.08
    pickle
    -0.08
    ocie
    -0.08
    çīĮåŃIJçļĦ
    -0.08
    )':
    -0.08
    esco
    -0.08
    STRU
    -0.07
    ä¸Ģå¼łå¼ł
    -0.07
    EMON
    -0.07
    POSITIVE LOGITS
    ber
    0.09
    apper
    0.07
    mo
    0.07
    oplan
    0.06
    代
    0.06
    maat
    0.06
    代为
    0.06
    ola
    0.06
    Doug
    0.06
     mou
    0.06
    Activations Density 0.823%

    No Known Activations