© 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. 63390
    Prev
    Next
    INDEX
    Explanations

    column-count

    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
    -0.07
    ↵
    -0.07
    ĥ
    -0.06
     instrument
    -0.06
    -0.06
    -0.05
    ↵↵
    -0.05
     Tomb
    -0.05
     reportedly
    -0.05
     industri
    -0.05
    POSITIVE LOGITS
    geführ
    0.09
    illère
    0.09
    æľ¬ç½ij
    0.08
    èĢĮä¸įè§ģ
    0.08
    uddle
    0.08
    antil
    0.08
    该款
    0.08
    attra
    0.08
    तिà¤ķ
    0.08
    åĪĨ许
    0.08
    Activations Density 0.025%

    No Known Activations