© 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. 42818
    Prev
    Next
    INDEX
    Explanations

    metabolites and metastases

    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
    /videos
    -0.07
    ennem
    -0.07
     Pett
    -0.07
    eters
    -0.07
    ½
    -0.07
    anh
    -0.06
    odd
    -0.06
    ©
    -0.06
    artos
    -0.06
    uppet
    -0.06
    POSITIVE LOGITS
    å¹´çļĦæŶéĹ´
    0.08
    à°°
    0.08
    æĪĸæľª
    0.07
    ä¸įèĥľ
    0.07
    kali
    0.07
    çijŀæĭī
    0.07
     abound
    0.07
    AAC
    0.07
    è£ħå¤ĩåĪ¶éĢł
    0.07
    à¹īà¸Ńม
    0.07
    Activations Density 0.079%

    No Known Activations