© 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. 55100
    Prev
    Next
    INDEX
    Explanations

    put / round instructions

    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
    Negative Logits
    ç®Ģ
    -0.06
     anywhere
    -0.06
    ughs
    -0.06
    éģį
    -0.06
     everywhere
    -0.06
    uite
    -0.06
     tasse
    -0.06
     Actu
    -0.06
    vá
    -0.06
    valt
    -0.06
    POSITIVE LOGITS
    ToFront
    0.09
    å®ĥä»¬åľ¨
    0.09
    å®ĥåľ¨
    0.08
    èı²å°Ķå¾·
    0.08
    dsl
    0.08
    ])/
    0.08
    omis
    0.08
    ARTA
    0.08
     inplace
    0.07
    icoli
    0.07
    Activations Density 0.330%

    No Known Activations