© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20641
    Prev
    Next
    INDEX
    Explanations

    computational complexity and operations

    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
    ebab
    -0.10
    ideon
    -0.09
    ameni
    -0.09
    adari
    -0.09
    ikian
    -0.09
    ranti
    -0.09
    ?url
    -0.08
    ullo
    -0.08
    æªĶ
    -0.08
    anio
    -0.08
    POSITIVE LOGITS
    è¿IJç®Ĺ
    0.07
    次æķ°
    0.07
     computational
    0.06
     operations
    0.06
    åıijçĶŁåľ¨
    0.06
    天河
    0.06
    å±±èį¯
    0.06
    ldr
    0.06
     per
    0.06
    大éĩıçļĦ
    0.06
    Activations Density 0.019%

    No Known Activations