© 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. 57337
    Prev
    Next
    INDEX
    Explanations

    Ghulam Hassan Bhat told AIR

    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
    جار
    -0.07
    _DA
    -0.07
    åĬŀåѦçIJĨ念
    -0.07
     Tid
    -0.06
     Blan
    -0.06
     Garrett
    -0.06
    å¼ĢéĻ¤
    -0.06
     Grat
    -0.06
    æĺĤæī¬
    -0.06
    ä¹ĭæĺŁ
    -0.06
    POSITIVE LOGITS
    æĪĸèĢħ缴æİ¥
    0.09
    没æľī帮åĬ©
    0.08
    uzzer
    0.07
    æĪĸ缴æİ¥
    0.07
    ilig
    0.07
    imap
    0.07
     roup
    0.07
    antar
    0.07
     ÑĥÑĩаÑģÑĤи
    0.07
    istra
    0.07
    Activations Density 0.008%

    No Known Activations