© 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. 38295
    Prev
    Next
    INDEX
    Explanations

    street address components

    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
    baugh
    -0.08
    åľŁæĸ¹
    -0.08
    礼
    -0.08
    åľŁåľ°ä½¿çĶ¨
    -0.07
    irl
    -0.07
    hofer
    -0.07
    ovil
    -0.07
    çł´æ¡Ī
    -0.07
    abut
    -0.07
    æĸ¹æĸ¹éĿ¢
    -0.07
    POSITIVE LOGITS
    undefined
    0.08
    ata
    0.07
    ffin
    0.07
    ignite
    0.06
    turn
    0.06
    æľ
    0.06
    èĥ½åĬĽåıĬ
    0.06
    ä¸Ģå¸Ĩ
    0.06
     niche
    0.06
    ibi
    0.06
    Activations Density 0.055%

    No Known Activations