© 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. 45019
    Prev
    Next
    INDEX
    Explanations

    obtain or produce results

    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
    bedingt
    -0.07
    **”
    -0.07
    asi
    -0.07
    ot
    -0.07
    odash
    -0.07
    utr
    -0.07
    çĤ¹åĩ»è¿Ľåħ¥
    -0.06
     \`
    -0.06
    èĢĮå¼Ĥ
    -0.06
    od
    -0.06
    POSITIVE LOGITS
    :
    0.08
    à¸Ķัà¸ĩà¸Ļีà¹ī
    0.07
    andia
    0.07
     bahwa
    0.07
    å¦Ĥä¸ĭ
    0.07
    ujan
    0.07
    à¹Ħà¸Ķà¹īวà¹Īา
    0.07
    ä»Ģä¹Īåij¢
    0.07
     arguably
    0.07
    ilda
    0.07
    Activations Density 0.011%

    No Known Activations