© 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. 3265
    Prev
    Next
    INDEX
    Explanations

    design, land, support, fields

    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
    enus
    -0.06
    大åħ¸
    -0.06
    ä½
    -0.06
    î
    -0.06
    å»Ĭ
    -0.06
    aders
    -0.06
    éĮĨ
    -0.06
    ãĥ«ãĥĢãĥ¼
    -0.05
    alar
    -0.05
    å·§
    -0.05
    POSITIVE LOGITS
    baugh
    0.07
    é£İ头
    0.07
     pur
    0.07
    Æ°u
    0.07
    warts
    0.07
    pector
    0.07
    æĪIJå½¢
    0.07
    åĩºä¸Ģ份
    0.07
    rawl
    0.07
    pur
    0.07
    Activations Density 0.328%

    No Known Activations