© 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. 39300
    Prev
    Next
    INDEX
    Explanations

    range [0,1]

    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
    gett
    -0.08
    ailed
    -0.08
    getc
    -0.07
    vs
    -0.07
     ench
    -0.07
    ieden
    -0.07
    çĦ°
    -0.07
    ondre
    -0.07
    nows
    -0.07
    usy
    -0.07
    POSITIVE LOGITS
    erah
    0.07
    éª
    0.07
     kÃŃ
    0.07
    atro
    0.07
    æ±IJ
    0.06
    贯彻èIJ½å®ŀ
    0.06
    .rand
    0.06
    å°§
    0.06
    طب
    0.06
    à¸Ĺร
    0.06
    Activations Density 0.026%

    No Known Activations