© 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. 39071
    Prev
    Next
    INDEX
    Explanations

    writing license

    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
    lott
    -0.10
    عت
    -0.09
    ..\
    -0.09
    Ñħол
    -0.08
    annis
    -0.07
    onan
    -0.07
    vog
    -0.07
    âłĢ
    -0.07
    KEN
    -0.07
    -0.07
    POSITIVE LOGITS
    ä¸ŃåİŁ
    0.06
    ity
    0.06
    éªij
    0.06
    æŃ¤é¡¹
    0.06
    è¾ķ
    0.06
     tá»ij
    0.06
    roy
    0.06
     cow
    0.06
     Gors
    0.06
    iff
    0.05
    Activations Density 0.005%

    No Known Activations