© 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. 4870
    Prev
    Next
    INDEX
    Explanations

    clearing, depletion, reduction, 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
    _past
    -0.08
    aney
    -0.07
    å½ĵãģ¦
    -0.07
     Savage
    -0.07
    inas
    -0.07
    inherit
    -0.07
    Ignore
    -0.07
    BOX
    -0.07
    åĬ©
    -0.07
    icias
    -0.07
    POSITIVE LOGITS
    à¹Ģหลืà¸Ń
    0.08
    åĩıå°ijäºĨ
    0.08
     depletion
    0.08
    åĩı
    0.08
    åĩıå°ij
    0.08
     reduction
    0.08
    ä¸įåĨįæľī
    0.08
    çķĻä¸ĭ
    0.07
     depleted
    0.07
    åİŁæľī
    0.07
    Activations Density 0.086%

    No Known Activations