© 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. 61261
    Prev
    Next
    INDEX
    Explanations

    Nokia CEO, Android Tablet, file_get_contents

    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
     appunto
    -0.09
    hoff
    -0.06
     Purt
    -0.06
    ardo
    -0.06
    infeld
    -0.06
    —but
    -0.06
    çľ©
    -0.06
    é¹ĥ
    -0.06
    çĬ¯ç½ªåĪĨåŃIJ
    -0.06
    या
    -0.06
    POSITIVE LOGITS
    ésp
    0.09
    è§Ħå®ļçļĦåħ¶ä»ĸ
    0.09
    ÙĪÛĮÙĩ
    0.08
    ÙĪاÙĦÙĬ
    0.07
    ejs
    0.07
    ัวรà¹Į
    0.07
    виÑı
    0.07
    çĤ¹èĩ³
    0.07
    espo
    0.07
    riture
    0.07
    Activations Density 0.194%

    No Known Activations