© 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. 15501
    Prev
    Next
    INDEX
    Explanations

    units and values

    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
    æī«çłģåħ³æ³¨
    -0.09
    indert
    -0.09
    áter
    -0.08
     Compon
    -0.08
    红衣
    -0.08
    :_
    -0.08
    LIA
    -0.08
    ÙĨÙģ
    -0.08
    è¤
    -0.08
    ething
    -0.08
    POSITIVE LOGITS
    asel
    0.06
    æŁ¥åĪ°
    0.06
    iecz
    0.06
    ä¸ĢåIJij
    0.06
    ife
    0.06
     k
    0.06
    adi
    0.06
    rt
    0.06
    att
    0.05
    миÑĤ
    0.05
    Activations Density 0.114%

    No Known Activations