© 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. 64202
    Prev
    Next
    INDEX
    Explanations

    names of people and measurements

    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
    èĢIJå¿ĥåľ°
    -0.07
    æıIJé«ĺèĩªèº«
    -0.06
    åıĪå¦Ĥä½ķ
    -0.06
    æĺ¯å½±åĵį
    -0.06
    ÙĪراÙĨ
    -0.06
    éļ¾çĤ¹éĹ®é¢ĺ
    -0.06
    人åİ»
    -0.06
     Sadd
    -0.06
     Zen
    -0.06
    èĴĤ
    -0.06
    POSITIVE LOGITS
    åį³
    0.09
    ãĥ³ãĤ°
    0.08
    åį§
    0.08
     czyli
    0.08
    马æĿ¥
    0.07
    åį³åľ¨
    0.07
    çļĦåľ°æŃ¥
    0.07
    äºĮéĥİ
    0.07
    ¥
    0.07
    ìķ½ìĿĦ
    0.07
    Activations Density 0.004%

    No Known Activations