© 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. 3475
    Prev
    Next
    INDEX
    Explanations

    camping and shelter constructions

    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
    çĶµæ¢¯
    -0.07
     cad
    -0.07
    æ³³
    -0.06
    ä¸Ĭ楼
    -0.06
     hallway
    -0.06
    åı¸
    -0.06
    ä¸ĢæĽ²
    -0.06
     Streets
    -0.06
    æ±łä¸Ń
    -0.06
    海峡
    -0.06
    POSITIVE LOGITS
    æIJŃ建
    0.13
     makeshift
    0.13
    ç®ĢéĻĭ
    0.12
    临æŶ
    0.12
    èIJ¥åľ°
    0.12
    éĢīåĿĢ
    0.11
    èIJ½èĦļ
    0.11
     constructions
    0.11
     improvised
    0.11
    å¸IJ篷
    0.10
    Activations Density 0.295%

    No Known Activations