© 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. 65014
    Prev
    Next
    INDEX
    Explanations

    LIVE HOUSE

    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
    åĪĩ
    -0.07
    ä¸Ĭæīĭ
    -0.06
    æ·¡å®ļ
    -0.06
    ajat
    -0.06
    bro
    -0.06
    UNDLE
    -0.05
    avec
    -0.05
    Dispatcher
    -0.05
    лежа
    -0.05
    Jwt
    -0.05
    POSITIVE LOGITS
    æģ¤
    0.09
    erso
    0.09
    ettings
    0.08
    Tunes
    0.08
    çĤ¹åĩ»æŁ¥çľĭçŃĶæ¡Ī
    0.07
     xì
    0.07
    ombe
    0.07
    ÑĤаки
    0.07
    èĬ®
    0.07
    visor
    0.07
    Activations Density 0.384%

    No Known Activations