© 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. 49192
    Prev
    Next
    INDEX
    Explanations

    [@bb ref ]

    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
     penetr
    -0.06
    éļ¾æ±Ĥ
    -0.06
    oni
    -0.06
    æī¿æĭħèµ·
    -0.06
    antro
    -0.06
     admittedly
    -0.06
    Esp
    -0.06
    nemonic
    -0.06
    umblr
    -0.06
    ES
    -0.06
    POSITIVE LOGITS
    illa
    0.07
    rever
    0.07
    fred
    0.07
    aventure
    0.07
    èµĦæĸĻ
    0.07
    ILLA
    0.07
    常çĶ¨çļĦ
    0.07
     fata
    0.07
    ersh
    0.07
     ioutil
    0.07
    Activations Density 0.160%

    No Known Activations