© 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. 7976
    Prev
    Next
    INDEX
    Explanations

    variable name followed by . or list/key

    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
    ault
    -0.08
    iad
    -0.08
    اÙĦÙĬ
    -0.07
    .Hosting
    -0.07
    ÙĪÛĮÛĮ
    -0.07
    nard
    -0.07
    rach
    -0.07
    ád
    -0.07
    ént
    -0.07
    nitz
    -0.07
    POSITIVE LOGITS
    è°·
    0.08
    èĸ
    0.07
     terp
    0.07
    èī²
    0.06
    à¹Ģหà¸Ļ
    0.06
     Emer
    0.06
    Ì
    0.06
    ä¾Ŀçħ§
    0.06
    享
    0.06
    idl
    0.06
    Activations Density 0.033%

    No Known Activations