© 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. 17478
    Prev
    Next
    INDEX
    Explanations

    recently up, direction of

    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
    æŃĮ
    -0.07
    ffre
    -0.07
    æĵİ
    -0.06
    matter
    -0.06
    idas
    -0.06
    amental
    -0.06
    estia
    -0.06
    ilibrium
    -0.06
    ahn
    -0.06
    御
    -0.06
    POSITIVE LOGITS
    ç¡®å®ŀæĺ¯
    0.08
    ä»ħæѤ
    0.08
    确认
    0.08
    ä¹Łä¼ļå½±åĵį
    0.07
    ä¸įä¼ļå½±åĵį
    0.07
    æĪij们å§ĭç»Ī
    0.07
     именно
    0.07
    erne
    0.07
    çī¹æľĹ
    0.07
     exactly
    0.07
    Activations Density 0.004%

    No Known Activations