© 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. 9403
    Prev
    Next
    INDEX
    Explanations

    calorimetric and scanning analysis

    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
    èĭ¦å¿ĥ
    -0.07
    æĽ´æĸ°æĹ¥æľŁ
    -0.07
    UpdatedAt
    -0.06
     Poe
    -0.06
    èĭ·
    -0.06
    ÑĦÑĢа
    -0.06
     NSURL
    -0.06
    ikke
    -0.06
     Stern
    -0.06
     selectedIndex
    -0.06
    POSITIVE LOGITS
    温差
    0.09
    åįĩ温
    0.09
    çĶµçĥŃ
    0.08
     heated
    0.08
     thermo
    0.08
     temperaturas
    0.08
     suhu
    0.08
     اÙĦØŃرارة
    0.08
     Peaks
    0.08
    åĨ·äºĨ
    0.08
    Activations Density 0.031%

    No Known Activations