© 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. 24647
    Prev
    Next
    INDEX
    Explanations

    units digit of

    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
    太大äºĨ
    -0.08
    主è¦ģåĨħ容
    -0.07
    avis
    -0.07
    大æ£ĢæŁ¥
    -0.07
     haj
    -0.06
    haj
    -0.06
    åįĹåĮĹéĢļéĢı
    -0.06
    æĢ»éĩı
    -0.06
    åĻ©
    -0.06
    ENC
    -0.06
    POSITIVE LOGITS
    loth
    0.09
     digit
    0.08
     digits
    0.08
    è¾ħ
    0.07
    _digit
    0.07
     cifra
    0.07
    egov
    0.07
     конÑĨов
    0.07
    digit
    0.07
    pressions
    0.07
    Activations Density 0.004%

    No Known Activations