© 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. 30285
    Prev
    Next
    INDEX
    Explanations

    numbers and finality

    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
    emme
    -0.08
    retto
    -0.07
    æĹłå¼Ĥ
    -0.07
    åıĪèĥ½
    -0.07
    çļĦè¿Ļç§į
    -0.07
    erval
    -0.07
     su
    -0.06
    ossi
    -0.06
    emm
    -0.06
    arkan
    -0.06
    POSITIVE LOGITS
     finally
    0.10
     infine
    0.09
     finalmente
    0.09
    finally
    0.08
     finalement
    0.08
     culmin
    0.08
     наконеÑĨ
    0.08
     finale
    0.08
     Finally
    0.08
     insgesamt
    0.08
    Activations Density 0.002%

    No Known Activations