© 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. 12364
    Prev
    Next
    INDEX
    Explanations

    I or Reader

    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
    èģĺä»»
    -0.06
    ibel
    -0.06
    å°Ħ
    -0.06
    uer
    -0.06
    éĹ´æŃĩ
    -0.06
    æĺ¯ä¸Ģ次
    -0.06
    åĴĮæī§è¡Į
    -0.06
    强身
    -0.06
    éĩıåĬĽ
    -0.06
    hatt
    -0.06
    POSITIVE LOGITS
    íĻĺ
    0.09
    .reference
    0.09
    ErrorMsg
    0.08
    byname
    0.08
    intr
    0.08
    åĪ®
    0.07
    .datab
    0.07
    åĩıåİ»
    0.07
    aggio
    0.07
    gross
    0.07
    Activations Density 0.001%

    No Known Activations