© 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. 26233
    Prev
    Next
    INDEX
    Explanations

    file descriptors, DLLs, String, bash

    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
    allback
    -0.07
    ogn
    -0.06
    å®ļ为
    -0.06
    åīį款
    -0.06
    æ²¹çĽIJ
    -0.06
    azol
    -0.06
    æĪijå°±ä¸į
    -0.06
     repet
    -0.06
     premature
    -0.06
    _wrap
    -0.06
    POSITIVE LOGITS
    çļĦéĢ»è¾ij
    0.09
    éĢ»è¾ij
    0.09
    ëģ¼
    0.09
     algebra
    0.09
    代æķ°
    0.09
    Logical
    0.08
     arithmetic
    0.08
     manipulation
    0.08
     logic
    0.08
    åĬłåĩı
    0.08
    Activations Density 0.187%

    No Known Activations