© 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. 47776
    Prev
    Next
    INDEX
    Explanations

    programming headers and keywords

    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
    ï¸ı
    -0.07
    -0.07
    åĨ³èµĽä¸Ń
    -0.07
    亦çĦ¶
    -0.07
    鼶åĶ®ä»·
    -0.07
    åĬ¡åħ¬å¼Ģ
    -0.07
    éĤ£é¢Ĺ
    -0.07
    .TryParse
    -0.06
     fullfile
    -0.06
     dites
    -0.06
    POSITIVE LOGITS
    алÑĥ
    0.08
     (((
    0.07
    ayani
    0.07
    æĸ¯åį¡
    0.07
    èĭį
    0.07
    aisen
    0.06
    åįģä¹Ŀ
    0.06
    hud
    0.06
    unya
    0.06
    çī¹
    0.06
    Activations Density 0.189%

    No Known Activations