© 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. 8294
    Prev
    Next
    INDEX
    Explanations

    B followed by and

    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
    è¿Ļä¹Łæĺ¯
    -0.06
    onz
    -0.06
    κά
    -0.06
    ìĪĺë¡ľ
    -0.06
    ãĥīãĤŃ
    -0.06
    ın
    -0.06
    å°Ķåħĭ
    -0.06
    /if
    -0.06
    æĿ¾
    -0.06
    ®
    -0.06
    POSITIVE LOGITS
     ê·¸ë¦¬ê³ł
    0.08
    ãģĿãģĹãģ¦
    0.08
    ãģ¨ãĤĤãģ«
    0.08
    çĸ½
    0.08
    çĴĢ
    0.08
    ä¹ĥèĩ³
    0.08
    sher
    0.08
     à¹ģละ
    0.07
     ect
    0.07
    edBy
    0.07
    Activations Density 0.023%

    No Known Activations