© 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. 56470
    Prev
    Next
    INDEX
    Explanations

    proper nouns and locations

    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
    allet
    -0.08
    заÑħ
    -0.07
    车è¾Ĩåľ¨
    -0.07
    jna
    -0.07
    å¼Ĥ
    -0.07
    æľĪä¸Ń
    -0.07
    ajari
    -0.07
    orget
    -0.07
    odon
    -0.07
    ÙĪاÙħ
    -0.06
    POSITIVE LOGITS
     again
    0.08
    both
    0.08
     both
    0.07
    again
    0.07
     Crosby
    0.07
     опÑıÑĤÑĮ
    0.07
    oner
    0.07
     Again
    0.07
     miscellaneous
    0.07
    æĹ¢
    0.07
    Activations Density 0.036%

    No Known Activations