© 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. 3725
    Prev
    Next
    INDEX
    Explanations

    alert calls

    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
    awl
    -0.07
    æĪijæĿ¥è¯´
    -0.06
    Mos
    -0.06
    æĹıèĩªæ²»åİ¿
    -0.06
     mos
    -0.06
    åIJ¹åĵį
    -0.06
     Mos
    -0.06
    orgia
    -0.06
    ampp
    -0.06
    对æĪijçļĦ
    -0.06
    POSITIVE LOGITS
    RIPT
    0.07
     setattr
    0.07
    itus
    0.07
    han
    0.07
    ança
    0.07
    iski
    0.07
    æ£ĺ
    0.07
    AndUpdate
    0.06
    cto
    0.06
     contests
    0.06
    Activations Density 0.076%

    No Known Activations