© 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. 19815
    Prev
    Next
    INDEX
    Explanations

    often followed by verbs

    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
    ãģĬãģĿãĤīãģı
    -0.10
    å®ŀè¯Ŀ
    -0.08
    eros
    -0.07
    Äįko
    -0.07
    zis
    -0.07
    opyright
    -0.07
     mera
    -0.07
     dioxide
    -0.07
     basically
    -0.07
    ëĦ
    -0.07
    POSITIVE LOGITS
    entimes
    0.13
     бÑĭваеÑĤ
    0.12
    -used
    0.11
    -times
    0.10
    кол
    0.10
     xuyên
    0.10
    ãģ¦
    0.10
     اÙĦØ£ØŃÙĬاÙĨ
    0.10
    ly
    0.09
     abbreviated
    0.09
    Activations Density 0.033%

    No Known Activations