© 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. 60998
    Prev
    Next
    INDEX
    Explanations

    increase or increasing something

    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
    tera
    -0.10
    çĽ¸ä¼¼æĸĩçĮ®
    -0.10
    kada
    -0.09
    à§įড
    -0.09
    ilestone
    -0.09
    etheless
    -0.09
    并èĮĤ
    -0.09
     заÑĤо
    -0.08
     (!((
    -0.08
    Ñĩей
    -0.08
    POSITIVE LOGITS
    /de
    0.10
    es
    0.10
    äºĨ对
    0.10
    ephy
    0.08
    OrUpdate
    0.08
     trÆ°á»Łng
    0.08
    oller
    0.08
    orre
    0.07
    ig
    0.07
    ividual
    0.07
    Activations Density 0.074%

    No Known Activations