© 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. 48136
    Prev
    Next
    INDEX
    Explanations

    "i" addressed

    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
    variant
    -0.08
    Ø©
    -0.08
    æŀ
    -0.08
    aurus
    -0.08
    ÙĨا
    -0.07
    ation
    -0.07
     somehow
    -0.07
     Neuer
    -0.07
    vari
    -0.07
    åıĭ
    -0.07
    POSITIVE LOGITS
    å¾·åŁº
    0.08
     Example
    0.07
    lus
    0.07
    ottom
    0.07
    $j
    0.06
    nique
    0.06
    yj
    0.06
    clearfix
    0.06
     Note
    0.06
    >f
    0.06
    Activations Density 0.003%

    No Known Activations