© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14848
    Prev
    Next
    INDEX
    Explanations

    addition or adding

    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
     alleine
    -0.07
     alone
    -0.07
     Alone
    -0.07
     itemprop
    -0.07
    /cs
    -0.07
    -alone
    -0.07
     salvo
    -0.07
    uld
    -0.07
    osis
    -0.06
     exclusively
    -0.06
    POSITIVE LOGITS
     added
    0.16
    æ·»åĬł
    0.15
    éĻĦåĬł
    0.15
     additions
    0.15
     addition
    0.14
     adds
    0.14
    é¢Ŀå¤ĸ
    0.13
    æ·»åĬłäºĨ
    0.13
     Addition
    0.13
     adding
    0.13
    Activations Density 0.153%

    No Known Activations