© 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. 49595
    Prev
    Next
    INDEX
    Explanations

    building stories or floors

    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
    岸边
    -0.08
    æ¦Ħ
    -0.08
    篱
    -0.08
     roadside
    -0.08
    WithType
    -0.07
    ÙĪج
    -0.07
    碰
    -0.07
    Road
    -0.07
    çľĭå®Ī
    -0.07
    è¾¹çķĮ
    -0.07
    POSITIVE LOGITS
    楼å±Ĥ
    0.11
     elevator
    0.10
     ÑįÑĤаж
    0.10
    楼çļĦ
    0.10
    å±ĤçļĦ
    0.10
    層
    0.10
    çĶµæ¢¯
    0.09
    夹å±Ĥ
    0.09
    楼
    0.09
     étage
    0.09
    Activations Density 0.064%

    No Known Activations