© 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. 55680
    Prev
    Next
    INDEX
    Explanations

    superpropyl)phosphate

    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
    baka
    -0.09
    ambang
    -0.09
    ÙĬض
    -0.08
    halte
    -0.08
    heu
    -0.08
    isting
    -0.08
    idon
    -0.08
    PTY
    -0.08
    ì±ħ
    -0.08
    aro
    -0.08
    POSITIVE LOGITS
    /
    0.06
    å°ģ
    0.06
    å¯Ĩå°ģ
    0.06
    åıĪä¸Ģ个
    0.06
    0.06
    (*)
    0.06
     بÙĦÙĨد
    0.06
    æľīç¦ı
    0.05
    [
    0.05
    æľīæĦŁ
    0.05
    Activations Density 0.003%

    No Known Activations