© 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. 56556
    Prev
    Next
    INDEX
    Explanations

    or / alternatives

    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
    è¦ģä¹Īæĺ¯
    -0.09
    è¦ģä¹Ī
    -0.09
     either
    -0.08
    adem
    -0.08
    either
    -0.07
    enaar
    -0.07
    Either
    -0.06
    æĬķèµĦæĪĸ
    -0.06
    éľĸ
    -0.06
     Either
    -0.06
    POSITIVE LOGITS
     alternatives
    0.10
     alternativas
    0.09
     alternativa
    0.09
     alternatively
    0.09
     alternativ
    0.08
     alternative
    0.08
     equivalente
    0.08
    edException
    0.08
     combinations
    0.08
    otherwise
    0.08
    Activations Density 0.235%

    No Known Activations