© 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. 10501
    Prev
    Next
    INDEX
    Explanations

    charged ions or cations

    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
    alap
    -0.08
    天ä»Ļ
    -0.07
    TERN
    -0.07
     Marche
    -0.07
    omento
    -0.07
    aim
    -0.07
    æ³Ľæ»¥
    -0.07
    ثر
    -0.06
    ä¸Ģåıij
    -0.06
    <<<<<<<
    -0.06
    POSITIVE LOGITS
    åħĭæĸ¯
    0.07
    缸å½ĵ
    0.07
    缸å½ĵäºİ
    0.07
    auj
    0.07
    æıIJ
    0.07
    æĭĶ
    0.07
    ÑģÑĤÑĢе
    0.07
     eduk
    0.07
    离åŃIJ
    0.07
    åĪĢ
    0.07
    Activations Density 0.004%

    No Known Activations