© 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. 39958
    Prev
    Next
    INDEX
    Explanations

    it 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
    mente
    -0.10
    hood
    -0.10
    hold
    -0.09
    Ùĭا
    -0.08
    ious
    -0.08
    à¹Ĩ
    -0.08
    heck
    -0.08
    hausen
    -0.08
    ×Ļ×Ķ
    -0.08
    ïque
    -0.08
    POSITIVE LOGITS
     own
    0.08
    inerary
    0.08
     же
    0.07
    iÅŁ
    0.07
    il
    0.07
    annis
    0.07
    iliz
    0.07
    self
    0.07
    uation
    0.06
    ablish
    0.06
    Activations Density 0.470%

    No Known Activations