© 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. 64737
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    ä¸įæīĵ
    -0.06
     parl
    -0.06
    çĥŃåĬĽ
    -0.06
    åį³ä¾¿å¦ĤæѤ
    -0.06
    åĪĩå®ŀåģļåĪ°
    -0.06
    æĹłæĢ¨æĹłæĤĶ
    -0.06
    -thumb
    -0.06
    -box
    -0.06
    å¦ĤæѤä¹ĭ
    -0.06
    çļĦæĢģ度
    -0.06
    POSITIVE LOGITS
    mira
    0.08
     netr
    0.08
    sap
    0.08
    eran
    0.07
     ÑģобÑĸ
    0.07
    åŁ¹
    0.07
    konom
    0.07
    zkod
    0.07
     vist
    0.07
    erschein
    0.07
    Activations Density 0.642%

    No Known Activations