© 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. 38142
    Prev
    Next
    INDEX
    Explanations

    consequence or result

    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
    好æĸĩ
    -0.09
    -prev
    -0.08
    _unpack
    -0.08
    UNG
    -0.08
    ä¸Ģ空
    -0.08
     ÐļÑĢаÑģи
    -0.08
    _PG
    -0.07
    пÑĢоÑĩем
    -0.07
     esfuerzos
    -0.07
     ìķĦëĭĪê³ł
    -0.07
    POSITIVE LOGITS
     Therefore
    0.08
     Hence
    0.07
     therefore
    0.07
    Therefore
    0.07
    æķħ
    0.07
    åĽłæѤ
    0.07
     aup
    0.06
    为ä»Ģä¹Ī说
    0.06
    Why
    0.06
    irm
    0.06
    Activations Density 0.045%

    No Known Activations