© 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. 45845
    Prev
    Next
    INDEX
    Explanations

    product of zero

    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
    GR
    -0.07
    认éĶĻ
    -0.07
    uron
    -0.07
     ref
    -0.06
     rigid
    -0.06
    å°Ĩæł¹æį®
    -0.06
    æĬĺ
    -0.06
    åĪ¶çļĦ
    -0.06
     inf
    -0.06
    æıIJç¥ŀ
    -0.06
    POSITIVE LOGITS
    iasco
    0.08
    次äºİ
    0.08
     Produit
    0.08
     transpose
    0.08
    imizer
    0.08
    è·¡
    0.08
    acker
    0.08
    emark
    0.08
    éĶ¦æłĩ
    0.08
    éĹ´æİ¥
    0.08
    Activations Density 0.004%

    No Known Activations