© 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. 32852
    Prev
    Next
    INDEX
    Explanations

    years

    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
    еÑĤÑĥ
    -0.07
    ÙģÙī
    -0.07
    eldon
    -0.07
    erne
    -0.06
    ¸
    -0.06
    ãģŁãĤĬ
    -0.06
    ï¾ŀ
    -0.06
    ght
    -0.06
    æī¿
    -0.06
    yse
    -0.06
    POSITIVE LOGITS
    gether
    0.12
    thon
    0.09
    åĽŀäºĭ
    0.09
    etheless
    0.09
    ation
    0.08
     اÙĦشأÙĨ
    0.08
    ertino
    0.08
    adays
    0.08
    ness
    0.08
    éĥ¨éŨèģĶåIJĪ
    0.08
    Activations Density 0.481%

    No Known Activations