© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23402
    Prev
    Next
    INDEX
    Explanations

    social and political actions

    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
    senz
    -0.07
    ëı
    -0.07
    паÑĢ
    -0.07
    åįĩåĪĿ
    -0.07
    renom
    -0.07
    åĩºåıijçĤ¹
    -0.06
    fels
    -0.06
    oon
    -0.06
    åij±åij±
    -0.06
    اÛĮÙĦ
    -0.06
    POSITIVE LOGITS
    èĪ¬çļĦ
    0.08
    èĪ¬åľ°
    0.07
    à¹ģหà¹Īà¸ĩ
    0.07
    lobal
    0.07
    ä¸Ģæł·çļĦ
    0.07
    zerű
    0.07
    Ī
    0.07
    aging
    0.07
    -like
    0.07
    èĪ¬
    0.07
    Activations Density 0.270%

    No Known Activations