© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2538
    Prev
    Next
    INDEX
    Explanations

    conservation

    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
    huizen
    -0.08
     nạ
    -0.08
    hood
    -0.08
    aylor
    -0.08
    çĶŁè¾ī
    -0.08
    kest
    -0.08
    à¹ģà¸Ķà¸ĩ
    -0.08
    ensore
    -0.07
    ä¸Ģæĸ°çļĦ
    -0.07
    weise
    -0.07
    POSITIVE LOGITS
    /reg
    0.08
    åĬŀåħ¬åİħ
    0.08
    Ùĩ
    0.08
    à¹Į
    0.07
    OrFail
    0.07
    ersions
    0.07
    धà¥Ģ
    0.07
    edett
    0.07
     vẹn
    0.07
    ervation
    0.07
    Activations Density 0.015%

    No Known Activations