© 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. 1956
    Prev
    Next
    INDEX
    Explanations

    LEGO figures and construction toys

    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
     fres
    -0.08
    ä¹ĭåīij
    -0.07
     pod
    -0.07
    opsis
    -0.07
    ath
    -0.06
    åīijæ°Ķ
    -0.06
    _CTX
    -0.06
     Tattoo
    -0.06
     ellipt
    -0.06
     Ell
    -0.06
    POSITIVE LOGITS
    ç§¯æľ¨
    0.12
    çİ©åħ·
    0.10
    çĽĬæĻº
    0.10
    æĭ¼è£ħ
    0.09
    ç»Ħè£ħ
    0.09
     LEGO
    0.09
    建æŀĦ
    0.09
    ä»¿çľŁ
    0.09
     toys
    0.09
     assemb
    0.09
    Activations Density 0.208%

    No Known Activations