© 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. 45951
    Prev
    Next
    INDEX
    Explanations

    licorice (Glycyrrhiza glabra)

    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
    ारà¥Ģ
    -0.08
    éŃĦåĬĽ
    -0.07
    çģŃç»Ŀ
    -0.07
    ibaba
    -0.07
    araf
    -0.07
    çĿ«æ¯Ľ
    -0.07
    alang
    -0.07
    èĥ½è§ģ度
    -0.07
    åĪ¹
    -0.07
    ebra
    -0.07
    POSITIVE LOGITS
    æ»ĭåħ»
    0.08
    ç¼ĵåĴĮ
    0.08
    大æŀ£
    0.07
    ç¾Į
    0.07
     ÑģмÑıг
    0.07
    æĬļ
    0.07
    å®īå¹³
    0.07
    åIJĪ
    0.07
    çIJ´
    0.07
    -rounded
    0.07
    Activations Density 0.001%

    No Known Activations