© 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. 61169
    Prev
    Next
    INDEX
    Explanations

    codes and identifiers

    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
    en
    -0.07
    za
    -0.06
    -0.06
    ä½Ĩæĺ¯å¯¹äºİ
    -0.06
    zon
    -0.06
    çĬ¶çļĦ
    -0.06
     .
    -0.06
    .X
    -0.06
     divert
    -0.06
    mer
    -0.05
    POSITIVE LOGITS
    åŁºéĩij管çIJĨ
    0.08
    ergestellt
    0.08
    _CMP
    0.08
     fotoc
    0.08
    ifar
    0.08
    pic
    0.08
    ä¸Ńéĸĵ
    0.08
    wski
    0.08
    olv
    0.08
    .WaitFor
    0.08
    Activations Density 0.040%

    No Known Activations