© 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. 45243
    Prev
    Next
    INDEX
    Explanations

    code variable names

    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
    asa
    -0.08
    gaard
    -0.07
    odb
    -0.07
     (!!
    -0.06
    çľĭå®ĪæīĢ
    -0.06
    \/
    -0.06
    )L
    -0.06
    æĺ¯èĩªå·±çļĦ
    -0.06
    бал
    -0.06
    zw
    -0.06
    POSITIVE LOGITS
    }`).
    0.08
    imps
    0.07
    urit
    0.07
    裾
    0.07
    LOAT
    0.07
    Adr
    0.07
     infatti
    0.07
     itself
    0.07
     bowiem
    0.06
    ovic
    0.06
    Activations Density 0.019%

    No Known Activations