© 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. 25604
    Prev
    Next
    INDEX
    Explanations

    primary elements

    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
     обез
    -0.07
     serv
    -0.07
    à¸ĩ
    -0.06
     ti
    -0.06
    uj
    -0.06
     thereafter
    -0.06
    pl
    -0.06
    æ±ł
    -0.06
    åıĪå¦Ĥä½ķ
    -0.06
    èĥĮåIJİ
    -0.06
    POSITIVE LOGITS
    è¡¥é½IJ
    0.10
    缺失
    0.09
     completing
    0.08
    并å®ĮæĪIJ
    0.08
    ียà¸Ķ
    0.08
    åį³åı¯å®ĮæĪIJ
    0.08
    еÑīа
    0.08
    egio
    0.08
    è£ľåħħ
    0.08
     completion
    0.08
    Activations Density 0.039%

    No Known Activations