© 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. 20733
    Prev
    Next
    INDEX
    Explanations

    solve, let, where

    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
    åīįèĢħ
    -0.06
    以ä¸ĭç®Ģ称
    -0.06
    è¿Ļç±»
    -0.06
    éĺµéĺµ
    -0.05
     ↵
    -0.05
    ÏĦÏģ
    -0.05
    inne
    -0.05
    -0.05
    åħħ
    -0.05
    åıį
    -0.05
    POSITIVE LOGITS
    acar
    0.09
    iguez
    0.08
    ẹt
    0.08
    acro
    0.08
    quÃŃ
    0.08
    olis
    0.08
    {}\
    0.08
    мога
    0.08
    strup
    0.08
    apur
    0.08
    Activations Density 0.090%

    No Known Activations