© 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. 13835
    Prev
    Next
    INDEX
    Explanations

    rigid objects

    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
    à¹Ģรืà¹Īà¸Ńยà¹Ĩ
    -0.08
    läss
    -0.07
    attered
    -0.07
    Ä«j
    -0.07
    eced
    -0.07
    ×Ļ×Ļ×Ŀ
    -0.07
    룴
    -0.07
    èī°è¾Ľ
    -0.07
    odore
    -0.07
     Caught
    -0.07
    POSITIVE LOGITS
    ness
    0.11
    ly
    0.11
    硬çļĦ
    0.09
    -flex
    0.08
    amente
    0.08
    esse
    0.08
    ç¨ĭ度
    0.08
    neck
    0.07
    -legged
    0.07
    idity
    0.07
    Activations Density 0.013%

    No Known Activations