© 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. 14907
    Prev
    Next
    INDEX
    Explanations

    numeric ranges or slices

    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
     incor
    -0.07
    etin
    -0.07
    ENN
    -0.07
     spectral
    -0.06
     sher
    -0.06
    èĢģäºĨ
    -0.06
    äck
    -0.06
    ÑģнÑĭй
    -0.06
    inta
    -0.06
    gow
    -0.06
    POSITIVE LOGITS
    å¼Ģå§ĭçļĦ
    0.08
    èµ·çĤ¹
    0.08
    åĸĢ
    0.08
    ÙĦÙĬا
    0.08
    ikli
    0.08
    å§ĭ
    0.08
     ì¤ijìĭ¬ìľ¼ë¡ľ
    0.07
    -start
    0.07
    èµ·å§ĭ
    0.07
    å§ĭèĩ³ç»Ī
    0.07
    Activations Density 0.018%

    No Known Activations