© 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. 8185
    Prev
    Next
    INDEX
    Explanations

    molten material jet

    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
    emd
    -0.07
    ä¸½å¨ľ
    -0.07
    esm
    -0.07
     меÑĢÑĤ
    -0.07
    resents
    -0.07
    sir
    -0.07
    UCA
    -0.07
    dings
    -0.07
    ENZA
    -0.07
    undai
    -0.07
    POSITIVE LOGITS
    åı¯èĥ½éľĢè¦ģ
    0.08
    hurst
    0.08
     somehow
    0.08
    aga
    0.07
    uga
    0.07
     whose
    0.07
    æīĢ欲
    0.07
    åľ¨æŁIJäºĽ
    0.07
    æĿĤ
    0.07
    åı¯èĥ½è¦ģ
    0.07
    Activations Density 0.013%

    No Known Activations