© 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. 21628
    Prev
    Next
    INDEX
    Explanations

    states or conditions

    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
     Norris
    -0.07
    ìĬµ
    -0.06
    eras
    -0.06
    à¸ģุม
    -0.06
    åıĬ使çĶ¨
    -0.06
    åĪĨç»Ħ
    -0.06
    äºİæĺ¯
    -0.06
    ieten
    -0.06
     ben
    -0.06
     глÑĥб
    -0.06
    POSITIVE LOGITS
    rels
    0.08
    TypeInfo
    0.07
    oples
    0.07
    atetime
    0.07
    istically
    0.07
    fds
    0.07
    Clickable
    0.07
    æĿijåĨħ
    0.07
    unning
    0.07
    íĥľ
    0.07
    Activations Density 0.014%

    No Known Activations