© 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. 21402
    Prev
    Next
    INDEX
    Explanations

    temporary or interim states

    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
    æĹłè®ºä»İ
    -0.09
    ä¸Ģéĥİ
    -0.07
    å¤
    -0.07
    éĢłå°±äºĨ
    -0.07
    åħĭç¦ı
    -0.07
    çĶ³
    -0.07
    ackt
    -0.07
    çIJĨæĥ³åĴĮ
    -0.07
    astery
    -0.07
    å¯ĮåĬĽ
    -0.07
    POSITIVE LOGITS
    æļĤæŶ
    0.22
    æļĤ
    0.21
    æļĤæŶçļĦ
    0.20
     temporarily
    0.19
    以å¾ħ
    0.17
    æļ«
    0.17
     until
    0.17
    æļ«æĻĤ
    0.17
     tạm
    0.16
    çŃīå¾ħ
    0.16
    Activations Density 0.312%

    No Known Activations