© 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. 13628
    Prev
    Next
    INDEX
    Explanations

    fin tail

    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
    Ø©
    -0.16
    entication
    -0.10
    ÑıÑĤа
    -0.09
     halnya
    -0.09
    à³įದ
    -0.09
    çŁ¥éģĵæĪij
    -0.08
    aufen
    -0.08
    ozilla
    -0.08
    ztat
    -0.08
    annels
    -0.08
    POSITIVE LOGITS
    ned
    0.10
    u
    0.09
    nya
    0.08
    imal
    0.08
    -
    0.08
    l
    0.08
    set
    0.08
    ter
    0.07
    p
    0.07
    ê¹IJ
    0.07
    Activations Density 0.003%

    No Known Activations