© 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. 13206
    Prev
    Next
    INDEX
    Explanations

    population growth and control

    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
     Zusamm
    -0.08
    union
    -0.08
    .Component
    -0.07
    ense
    -0.07
    éĽ¨éĽª
    -0.07
    éľĵ
    -0.07
     ìĿ´ëĵ¤ìĿĺ
    -0.07
    æŀĦæĪIJ
    -0.07
    äºĶè°·
    -0.07
    éĵ¶å±±
    -0.07
    POSITIVE LOGITS
    ç¹ģæ®ĸ
    0.09
     growth
    0.08
    æ®ĸ
    0.08
    growth
    0.08
     Growth
    0.08
    éģıåĪ¶
    0.07
     slowing
    0.07
    _growth
    0.07
    模åŀĭ
    0.07
     fertility
    0.07
    Activations Density 0.004%

    No Known Activations