© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61613
    Prev
    Next
    INDEX
    Explanations

    .Controls; .Media; .Forms; .Diagnostics

    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
    使çĶ¨æŶéĹ´
    -0.08
    çijŀæĭī
    -0.07
    人ä¸Ģ
    -0.07
    à¹Īาà¸Ļ
    -0.07
    òa
    -0.07
    epam
    -0.07
    utum
    -0.07
    ayment
    -0.07
    áĢģ
    -0.07
    деÑĢжка
    -0.06
    POSITIVE LOGITS
    æ»Ķ
    0.07
    以ä¸ĭç®Ģ称
    0.07
    åı¸
    0.06
    .*
    0.06
    éŀł
    0.06
    inqu
    0.06
    ORE
    0.06
    æĸ©
    0.06
    boats
    0.06
    irie
    0.06
    Activations Density 0.319%

    No Known Activations