© 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. 55639
    Prev
    Next
    INDEX
    Explanations

    essays, research, plot, topics

    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
    æł¹æį®å®ŀéĻħæĥħåĨµ
    -0.07
     Geb
    -0.07
    æĢ¥
    -0.07
    çİ°å®ŀä¸Ń
    -0.06
    ock
    -0.06
    ä»İæĪijåģļèµ·
    -0.06
    缸åħ³èµĦ讯
    -0.06
    olicy
    -0.06
    æĽ´æĸ°
    -0.06
    缸åħ³çŁ¥è¯Ĩ
    -0.06
    POSITIVE LOGITS
    åĪĨæŀIJæ³ķ
    0.11
     analyzing
    0.10
     analyses
    0.10
    æı£æij©
    0.10
    åĪĨæŀIJæĸ¹æ³ķ
    0.10
     extracts
    0.09
    åĪĨæŀIJçļĦ
    0.09
     ë¶ĦìĦĿ
    0.09
     interpretations
    0.09
     textual
    0.09
    Activations Density 0.147%

    No Known Activations