© 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. 56013
    Prev
    Next
    INDEX
    Explanations

    virtual

    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
     acostumbr
    -0.08
    winkel
    -0.08
    iare
    -0.08
    ä¸ĢæľĽ
    -0.08
     Äijầm
    -0.07
     asegurado
    -0.07
    пеÑĤÑĮ
    -0.07
    inales
    -0.07
     Loader
    -0.07
    ingan
    -0.07
    POSITIVE LOGITS
     equivalent
    0.09
    åıĺ缸
    0.09
     virtual
    0.09
     indirectly
    0.08
    ç²¾ç¥ŀä¸ĬçļĦ
    0.08
     virtuale
    0.08
    äºĨä¸Ģæł·
    0.08
     effectively
    0.08
    çŃīæķĪ
    0.08
    çļĦæķĪæŀľ
    0.08
    Activations Density 0.233%

    No Known Activations