© 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. 65138
    Prev
    Next
    INDEX
    Explanations

    following a note

    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
     Benson
    -0.08
    åħ·ä½ĵæĿ¥è¯´
    -0.08
    ictured
    -0.07
    ãģĤãĤĭ
    -0.07
    åIJįå±±
    -0.07
    شد
    -0.07
    ERSIST
    -0.07
     pitch
    -0.07
    ä¸Ģ个åı«
    -0.07
    åħĭç¦ı
    -0.07
    POSITIVE LOGITS
    anser
    0.08
    oard
    0.08
    åľ¨ä»¥åIJİ
    0.08
    ç³»
    0.07
     bahwa
    0.07
    oire
    0.07
    enea
    0.07
    å¦ĤéľĢ
    0.07
    åĩłå£°
    0.07
    eware
    0.07
    Activations Density 0.012%

    No Known Activations