© 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. 65118
    Prev
    Next
    INDEX
    Explanations

    links or source file

    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
    ylv
    -0.07
     Trilogy
    -0.07
    éĢģä¸Ģ
    -0.07
    iagnostics
    -0.07
    abcdefghijklmnop
    -0.07
    ative
    -0.07
    riad
    -0.06
    çĿĢä¸ĢèĤ¡
    -0.06
    :href
    -0.06
    ---</
    -0.06
    POSITIVE LOGITS
    å¦Ī
    0.07
    пÑĭ
    0.07
    媽
    0.07
    اÙģÙĬØ©
    0.07
    eppe
    0.07
     kokem
    0.06
    ciam
    0.06
    大ä¸Ń
    0.06
    é£ĺé£ĺ
    0.06
     lòng
    0.06
    Activations Density 0.001%

    No Known Activations