© 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. 25330
    Prev
    Next
    INDEX
    Explanations

    a copy or choice

    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
     in
    -0.08
     and
    -0.08
     intuition
    -0.08
    u
    -0.08
     as
    -0.07
     opera
    -0.07
     an
    -0.07
     along
    -0.07
    jera
    -0.07
     alleg
    -0.07
    POSITIVE LOGITS
    æĪĸå¤ļ个
    0.16
    /an
    0.11
    ustin
    0.10
    theros
    0.10
    iken
    0.10
    esthetic
    0.10
    eration
    0.10
    åIJįåı«
    0.10
    cls
    0.10
    resh
    0.09
    Activations Density 1.864%

    No Known Activations