© 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. 26721
    Prev
    Next
    INDEX
    Explanations

    consecutive or together

    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
     ÑģемейÑģÑĤва
    -0.08
    mens
    -0.08
    ataka
    -0.07
    iché
    -0.07
    iaux
    -0.07
    å¾IJæŁIJ
    -0.07
    illed
    -0.07
     kebe
    -0.07
    ç¥ŀéĩĩ
    -0.07
    PHA
    -0.07
    POSITIVE LOGITS
    ä¸įæķ£
    0.08
    åľ¨ä¸Ģèµ·çļĦ
    0.08
     together
    0.08
     Separ
    0.07
     separation
    0.07
     placement
    0.07
     anywhere
    0.07
    鼶è·Ŀ离
    0.07
    åĪĨå¼Ģ
    0.06
     grouping
    0.06
    Activations Density 0.005%

    No Known Activations