© 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. 30075
    Prev
    Next
    INDEX
    Explanations

    solve for variables

    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
    alker
    -0.08
    imps
    -0.07
    Ñįм
    -0.07
    ese
    -0.07
    çī¹æĸ°
    -0.07
    ãģľ
    -0.07
    ikt
    -0.07
    大åĬ¿
    -0.07
    ideo
    -0.07
    å·¥ä½ľéĩı
    -0.07
    POSITIVE LOGITS
     fér
    0.08
    çĺ¾
    0.07
    à¸ķัว
    0.07
    轻轻çļĦ
    0.07
    ãģıãĤĵ
    0.07
    avy
    0.07
    ç»ĻæĪijçķĻè¨Ģ
    0.07
    è¯»æľ¬
    0.06
    èĮĥåĽ´
    0.06
    inois
    0.06
    Activations Density 0.033%

    No Known Activations