© 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. 19946
    Prev
    Next
    INDEX
    Explanations

    temp table or projected space

    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
    $\
    -0.06
    ä¹ĭäºİ
    -0.06
    Ù°
    -0.06
     $\
    -0.06
    $$
    -0.06
    ${
    -0.06
    ·
    -0.06
    $$$$
    -0.05
     analyzes
    -0.05
    inach
    -0.05
    POSITIVE LOGITS
    âĢIJ
    0.11
    обе
    0.08
    åħ¨èĥľ
    0.08
     SAME
    0.08
    lick
    0.08
    æµıè§Ī次æķ°
    0.08
    opy
    0.08
    âĢij
    0.08
    ivent
    0.07
    æĭĦ
    0.07
    Activations Density 0.002%

    No Known Activations