© 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. 29985
    Prev
    Next
    INDEX
    Explanations

    optical properties of dB/cm

    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
    æĬ¢åįł
    -0.09
    WM
    -0.07
    ç§ĭåįĥ
    -0.07
    æŶéĹ´çĤ¹
    -0.07
     sched
    -0.07
    ellini
    -0.07
     Oval
    -0.07
     late
    -0.07
    YNC
    -0.07
    FieldValue
    -0.06
    POSITIVE LOGITS
    沿éĢĶ
    0.10
     exponential
    0.10
     attenuation
    0.09
     expon
    0.09
    è¡°åĩı
    0.09
     Beer
    0.08
    éĢĶä¸Ń
    0.08
    æįŁèĢĹ
    0.08
     пÑĢоÑħождениÑı
    0.08
     exponentially
    0.08
    Activations Density 0.009%

    No Known Activations