© 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. 58753
    Prev
    Next
    INDEX
    Explanations

    positive/negative sentiment or direction

    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
    rock
    -0.09
    opt
    -0.07
    çļĦæĸ°é²ľ
    -0.07
    =YES
    -0.07
    åįģä¹Ŀç«ł
    -0.07
    å±Ĥ级
    -0.07
    лоÑģÑĮ
    -0.07
    交éĢļäºĭæķħ责任
    -0.07
    HEST
    -0.06
    лл
    -0.06
    POSITIVE LOGITS
    æŃ£åĢ¼
    0.12
     positive
    0.10
     negative
    0.09
    为æŃ£
    0.09
     positif
    0.09
    egative
    0.09
    -positive
    0.09
     positivo
    0.08
     inverted
    0.08
    positive
    0.08
    Activations Density 0.004%

    No Known Activations