© 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. 28788
    Prev
    Next
    INDEX
    Explanations

    part of or belongs

    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
    enner
    -0.10
    mdl
    -0.09
    ://'
    -0.08
    ä¹ĭäºİ
    -0.08
    mata
    -0.08
    AndView
    -0.08
    æľīå¿ĥ人
    -0.08
    ä¸Ģä¸ªäººåľ¨
    -0.08
    åĴĮåĨħ容
    -0.08
    StringEncoding
    -0.08
    POSITIVE LOGITS
    owie
    0.06
    ,
    0.06
    以åıĬ对
    0.06
    ...
    0.06
    je
    0.06
    ï¼Į
    0.05
    并æİ¥åıĹ
    0.05
     je
    0.05
    以åıĬåľ¨
    0.05
    ä¿ĿæĮģ稳å®ļ
    0.05
    Activations Density 0.028%

    No Known Activations