© 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. 12337
    Prev
    Next
    INDEX
    Explanations

    affirmation, correctness, or approval

    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
    åħĭæĸ¯
    -0.08
    iha
    -0.07
    ê²łì£ł
    -0.07
    acz
    -0.07
    nicz
    -0.07
    abra
    -0.07
    å°ıæľī
    -0.07
     kalinya
    -0.07
    avar
    -0.07
    æĹ¥å¤ľ
    -0.07
    POSITIVE LOGITS
    ноÑģ
    0.07
    aye
    0.07
    uen
    0.07
    AY
    0.07
    à¹ĥà¸Ļà¸IJาà¸Ļะ
    0.07
    ÙĦÙħ
    0.07
    ÃŃce
    0.07
    (crate
    0.06
    над
    0.06
    é¡Į
    0.06
    Activations Density 0.003%

    No Known Activations