© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 4589
    Prev
    Next
    INDEX
    Explanations

    instrument parts and additions

    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
    åŁºçĤ¹
    -0.07
    ÑĦло
    -0.07
    anas
    -0.07
    WORDS
    -0.07
     republ
    -0.07
    å¨ħ
    -0.07
    åĪĨ许
    -0.07
    ¶ļ
    -0.07
    VERR
    -0.07
    .OUT
    -0.07
    POSITIVE LOGITS
     Instruments
    0.07
     instrument
    0.07
    æĦŁæģ©çļĦå¿ĥ
    0.07
    iri
    0.06
     add
    0.06
    dit
    0.06
    äsch
    0.06
     Add
    0.06
     instruments
    0.06
     Together
    0.06
    Activations Density 0.096%

    No Known Activations