© 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. 57928
    Prev
    Next
    INDEX
    Explanations

    numbers in parentheses

    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
    ,
    -0.08
    1
    -0.07
     other
    -0.06
    5
    -0.06
    对å°ı
    -0.06
    åħ¶ä»ĸ
    -0.05
    åħ¶ä»ĸçļĦ
    -0.05
    2
    -0.05
    rot
    -0.05
     v
    -0.05
    POSITIVE LOGITS
    ðŁĻĤ
    0.09
    渡åģĩ
    0.09
    artigen
    0.09
    ISTR
    0.09
    vrier
    0.09
    issé
    0.09
    autés
    0.09
    ðŁĺĢ
    0.09
    ensis
    0.09
    aux
    0.09
    Activations Density 0.014%

    No Known Activations