© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44829
    Prev
    Next
    INDEX
    Explanations

    thinking processes

    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
    orary
    -0.08
    itious
    -0.08
    issimo
    -0.08
    jev
    -0.08
    ensed
    -0.08
    ¾
    -0.07
    Writable
    -0.07
    onet
    -0.07
    ÃŃss
    -0.07
    issima
    -0.07
    POSITIVE LOGITS
    richtung
    0.09
    å¤Ħäºĭ
    0.08
    Ñĩки
    0.08
    fuck
    0.07
    æĢĿç»´
    0.07
     thinking
    0.07
    ä¹łæĥ¯äºĨ
    0.07
    æĢĿç»´çļĦ
    0.07
    ç¿Ĵæħ£
    0.07
    richtungen
    0.07
    Activations Density 0.014%

    No Known Activations