© 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. 17199
    Prev
    Next
    INDEX
    Explanations

    argued the cause

    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
    çī¹å²Ĺ
    -0.09
    ocracy
    -0.07
    æĥħ人
    -0.07
    tage
    -0.07
    itar
    -0.06
     Wenger
    -0.06
    ycz
    -0.06
     espec
    -0.06
    便äºİ
    -0.06
    以åıĬåIJĦç§į
    -0.06
    POSITIVE LOGITS
    igm
    0.07
    toh
    0.07
    pike
    0.07
    å¾Ĺ主
    0.07
    .lu
    0.07
    пи
    0.06
    zim
    0.06
    eks
    0.06
    (getResources
    0.06
    æ®ĸ
    0.06
    Activations Density 0.001%

    No Known Activations