© 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. 2368
    Prev
    Next
    INDEX
    Explanations

    name parts and suffixes

    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
    ew
    -0.08
    simd
    -0.07
    ä¸Ģç»ı
    -0.07
    å®ļè¦ģ
    -0.07
    bet
    -0.07
    çĥŃéŨæIJľç´¢
    -0.07
    åĩºæģ¯
    -0.07
    ordes
    -0.07
    unks
    -0.07
    .pixel
    -0.06
    POSITIVE LOGITS
    è¢«ä½ł
    0.07
    feuille
    0.07
    .WriteHeader
    0.06
    éĺħ读åħ¨æĸĩ
    0.06
    -ing
    0.06
    æĥ³ä½ł
    0.06
    æļĹ
    0.06
    ilier
    0.06
    éĤĥ
    0.06
    ingles
    0.06
    Activations Density 0.013%

    No Known Activations