© 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. 55168
    Prev
    Next
    INDEX
    Explanations

    remove / removal

    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
    ï¸İ
    -0.09
     ulang
    -0.09
    nect
    -0.09
    thouse
    -0.09
    åĮĸåıijå±ķ
    -0.08
    abri
    -0.08
    ownie
    -0.08
    uale
    -0.08
    atures
    -0.08
    nection
    -0.08
    POSITIVE LOGITS
    /add
    0.11
     khá»ıi
    0.09
    PTION
    0.08
    æ®Ĩå°½
    0.08
    /re
    0.08
    ive
    0.08
    /rem
    0.08
    es
    0.08
    æĪij社
    0.07
    able
    0.07
    Activations Density 0.045%

    No Known Activations