© 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. 38011
    Prev
    Next
    INDEX
    Explanations

    what is

    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
    声èī²
    -0.08
    دÙĬر
    -0.08
     Cupertino
    -0.07
    entre
    -0.07
    ially
    -0.07
     Las
    -0.07
     Fanpage
    -0.07
    -fw
    -0.07
    udel
    -0.07
    entes
    -0.06
    POSITIVE LOGITS
    éĺħ读åħ¨æĸĩ
    0.08
    诣
    0.07
     bout
    0.07
    zil
    0.07
     же
    0.07
     знаком
    0.07
    屯
    0.07
    orf
    0.07
    å¦Ĥä½ķæıIJé«ĺ
    0.07
    ricks
    0.06
    Activations Density 0.079%

    No Known Activations