© 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. 29751
    Prev
    Next
    INDEX
    Explanations

    V, D, H variable names

    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
    gether
    -0.07
     Wend
    -0.06
    ãģªãģı
    -0.06
     unfortunate
    -0.06
    éĩijåŁİ
    -0.06
     Ponte
    -0.06
    çŁ¥ä¹ĭ
    -0.06
    ç¦ıå¾·
    -0.06
    çĶŁçļĦ
    -0.05
    _patches
    -0.05
    POSITIVE LOGITS
    ertz
    0.08
    eres
    0.08
    enje
    0.08
    inia
    0.08
    esc
    0.08
    rish
    0.07
    å°Ķåħĭ
    0.07
    gesamt
    0.07
    ä¸Ģæĺ¯è¦ģ
    0.07
                    ↵                ↵
    0.07
    Activations Density 0.034%

    No Known Activations