© 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. 12653
    Prev
    Next
    INDEX
    Explanations

    `String email` `controller` `Write` `zoom` `first` `densities` `necessary`

    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
    麦å½ĵ
    -0.08
    å°±çĽ®åīį
    -0.08
    iese
    -0.07
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    -0.07
    éľĢè°¨æħİ
    -0.07
    .Error
    -0.07
    å½¢èī²
    -0.07
    .nd
    -0.07
     neither
    -0.07
     accompanies
    -0.07
    POSITIVE LOGITS
    ä¸ĸçķĮä¸Ĭ
    0.07
    ði
    0.07
    çļĦç¡®
    0.07
    æłĩåħµ
    0.07
    ãĢģ
    0.07
    çİĭåĽ½
    0.06
    embe
    0.06
    Overrides
    0.06
    req
    0.06
    çĶ»ä¸Ĭ
    0.06
    Activations Density 0.031%

    No Known Activations