© 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. 55952
    Prev
    Next
    INDEX
    Explanations

    css -webkit- properties

    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
    acific
    -0.07
    ÙħÙĪد
    -0.07
    aup
    -0.07
    å½ĵåħ¶
    -0.07
    AndWait
    -0.07
    елÑı
    -0.06
    åıįä¹ĭ
    -0.06
    adÃŃ
    -0.06
    -au
    -0.06
    yum
    -0.06
    POSITIVE LOGITS
    ¿
    0.08
    åĥ»
    0.07
    çªģåĩºéĩįçĤ¹
    0.07
    iddle
    0.07
    үй
    0.07
    è·³åĩº
    0.06
    彿
    0.06
    utos
    0.06
    inder
    0.06
    othi
    0.06
    Activations Density 0.001%

    No Known Activations