© 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. 58007
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    模èĮĥ
    -0.09
    xca
    -0.08
    ä¸ŃåĽ½ç«Ļ
    -0.08
    ÙģÙĬات
    -0.08
    åĽ½å®¶éĩįçĤ¹
    -0.08
     Annunci
    -0.08
    åķ§åķ§
    -0.08
    æĪijè¦ģè¯Ħ论
    -0.08
    aptive
    -0.08
    åħįè´¹åľ¨çº¿
    -0.07
    POSITIVE LOGITS
    anst
    0.07
    uru
    0.07
    ities
    0.06
    anke
    0.06
    =utf
    0.06
    ville
    0.06
    legen
    0.06
    å¾Ĺå¿ĥ
    0.06
     civ
    0.06
    ank
    0.06
    Activations Density 0.000%

    No Known Activations