© 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. 42128
    Prev
    Next
    INDEX
    Explanations

    numbers and indexing

    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
    emma
    -0.07
     Cherry
    -0.07
    ä¸Ģç§į
    -0.06
    æĵį
    -0.06
    æŀī
    -0.06
    åIJĮ人
    -0.06
    ères
    -0.06
    ISMO
    -0.06
    å¿į
    -0.06
    erot
    -0.06
    POSITIVE LOGITS
    å¦ĩ产
    0.08
    agini
    0.08
    andung
    0.08
    é£ŁãģĦ
    0.07
    æľĽçĿĢ
    0.07
    icul
    0.07
    éĢĨ
    0.07
    .ov
    0.07
     Fron
    0.07
    .DataTable
    0.07
    Activations Density 0.004%

    No Known Activations