© 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. 58719
    Prev
    Next
    INDEX
    Explanations

    specific names and numbers

    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
    as
    -0.07
    se
    -0.06
    D
    -0.06
    ake
    -0.06
    i
    -0.06
    d
    -0.06
    C
    -0.06
    اÙĪÙĦ
    -0.06
    J
    -0.06
    acc
    -0.06
    POSITIVE LOGITS
     **:**
    0.09
    olucion
    0.09
    áīł
    0.09
     sekal
    0.08
     abbast
    0.08
    ingleton
    0.08
    венÑĤа
    0.08
    ekali
    0.08
    zeÅĽ
    0.08
    èŁĨ
    0.08
    Activations Density 0.008%

    No Known Activations