© 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. 13428
    Prev
    Next
    INDEX
    Explanations

    channels and mediums

    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
    ooth
    -0.08
    çīĪæĿĥå½Ĵ
    -0.06
     mildly
    -0.06
     Bene
    -0.06
     AABB
    -0.06
    .reason
    -0.06
    lesi
    -0.06
     Hunter
    -0.06
    ÑĪаÑĤ
    -0.06
    DirectoryName
    -0.06
    POSITIVE LOGITS
     mediums
    0.14
    æ¸łéģĵ
    0.12
    æīĭ段
    0.12
    åªĴä»ĭ
    0.11
    è½½ä½ĵ
    0.11
    éĢĶå¾Ħ
    0.11
    channels
    0.11
    å¤ļç§įæĸ¹å¼ı
    0.11
     channels
    0.11
    /modal
    0.10
    Activations Density 0.198%

    No Known Activations