© 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. 13087
    Prev
    Next
    INDEX
    Explanations

    essential, crucial, important

    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
    æľīå¿ĥ人
    -0.09
    biet
    -0.08
    opak
    -0.08
    ebut
    -0.08
    åĽ¾çīĩæĪĸ
    -0.08
    föl
    -0.08
    xada
    -0.08
    为ä»Ģä¹Īåij¢
    -0.08
    burgh
    -0.08
    åĬłåħ¥ä¹¦æŀ¶
    -0.08
    POSITIVE LOGITS
     important
    0.09
    çŃīéĩįè¦ģ
    0.08
     crucial
    0.08
     essential
    0.08
     Important
    0.08
     vital
    0.07
     fundamental
    0.07
    éĩįè¦ģçļĦ
    0.07
    éĩįè¦ģãģª
    0.07
    éĩįè¦ģ
    0.07
    Activations Density 0.303%

    No Known Activations