© 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. 42171
    Prev
    Next
    INDEX
    Explanations

    contraction or possessive + common word

    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
    ances
    -0.09
    itale
    -0.08
    antes
    -0.08
     internals
    -0.07
    ania
    -0.07
     former
    -0.07
    çŁ£
    -0.07
    amiento
    -0.07
    ance
    -0.07
    etat
    -0.07
    POSITIVE LOGITS
    æ¸ħç®Ĺ
    0.07
    ä¸»é£Ł
    0.07
    åIJĥçļĦ
    0.07
     réforme
    0.07
    çī¹å°Ķ
    0.07
    ikh
    0.07
    æĶ
    0.06
    éĢĨè¡Į
    0.06
    åħ¨åĮº
    0.06
    itzer
    0.06
    Activations Density 0.031%

    No Known Activations