© 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. 42832
    Prev
    Next
    INDEX
    Explanations

    IMEI Unlock Code

    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
    æĹłäºĭ
    -0.07
    æİ¢
    -0.07
    ä¿®
    -0.06
    ("<?
    -0.06
    unami
    -0.06
    IDAS
    -0.06
    éĻ¢
    -0.06
    毫æĹł
    -0.06
    à¸Ļà¹Īา
    -0.06
    zac
    -0.06
    POSITIVE LOGITS
    ¿
    0.08
    ibase
    0.07
    еÑĢбÑĥ
    0.07
     linda
    0.07
    å¸Ī表
    0.07
    elight
    0.07
    mila
    0.07
    eral
    0.07
    楷
    0.07
    çĶŁäºİ
    0.07
    Activations Density 0.001%

    No Known Activations