© 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. 12424
    Prev
    Next
    INDEX
    Explanations

    domain inequalities

    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
    zelfde
    -0.07
    ë¡ľ
    -0.07
    s
    -0.07
    غ
    -0.07
    幸ç¦ıçĶŁæ´»
    -0.07
    ÏĩÏį
    -0.06
    .idea
    -0.06
    en
    -0.06
    izes
    -0.06
    ureau
    -0.06
    POSITIVE LOGITS
    ness
    0.14
    ï¸ı
    0.11
    Ø©
    0.10
    0.10
    theless
    0.10
    ingly
    0.10
    ation
    0.10
    gether
    0.09
     nhau
    0.09
    sl
    0.09
    Activations Density 0.004%

    No Known Activations