© 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. 19990
    Prev
    Next
    INDEX
    Explanations

    circle, spheres, password, networks

    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
     breakdown
    -0.07
    宦
    -0.07
    .eth
    -0.06
    ale
    -0.06
    æī¹ç¤º
    -0.06
    å©ķ
    -0.06
    åĤ¬äºº
    -0.06
    enso
    -0.06
     disag
    -0.06
    大å°Ĩ
    -0.06
    POSITIVE LOGITS
    åľĪ
    0.08
     circle
    0.07
    ysh
    0.07
    çĶŁæĢģåľĪ
    0.07
    æ±Ģ
    0.07
    (circle
    0.07
     recipro
    0.07
    -circle
    0.07
    rix
    0.07
    maa
    0.07
    Activations Density 0.004%

    No Known Activations