© 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. 45348
    Prev
    Next
    INDEX
    Explanations

    Received / Accepted dates

    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
    CreateInfo
    -0.07
    æ··ä¹±
    -0.07
    èĬĻèĵī
    -0.06
    à¸£à¸´à¸Ľ
    -0.06
     recip
    -0.06
    Rand
    -0.06
    仪
    -0.06
    ário
    -0.06
    æĽ¾åĽ½
    -0.06
    æģ¶æĢ§èĤ¿çĺ¤
    -0.06
    POSITIVE LOGITS
    é«ĺåĪĨ
    0.07
     Gerhard
    0.07
    å¾Īå¿«å°±ä¼ļ
    0.07
     ÙĨظر
    0.07
    ERG
    0.07
    åıĪå¦Ĥ
    0.07
    éķ¶åµĮ
    0.06
    иÑģÑĤÑĢа
    0.06
    acks
    0.06
    etal
    0.06
    Activations Density 0.012%

    No Known Activations