© 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. 28659
    Prev
    Next
    INDEX
    Explanations

    description

    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
    jeta
    -0.08
    åIJİèĢħ
    -0.07
    els
    -0.07
    urally
    -0.07
    为å®ĺ
    -0.06
    teni
    -0.06
    lers
    -0.06
    rels
    -0.06
    å°Ĩ士
    -0.06
     Shape
    -0.06
    POSITIVE LOGITS
    ģ
    0.07
    phinx
    0.07
    ibbon
    0.07
    UNCH
    0.07
    ãĢĢ
    0.07
    quo
    0.07
    ä½Ĩä¸įéĻIJäºİ
    0.07
    %!
    0.07
    agra
    0.07
    OLF
    0.07
    Activations Density 0.173%

    No Known Activations