© 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. 63748
    Prev
    Next
    INDEX
    Explanations

    email signatures or past tense verbs

    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
    onse
    -0.08
    æ°´éĩĮ
    -0.08
     Juda
    -0.07
    梦éĩĮ
    -0.07
    allocator
    -0.07
     argc
    -0.07
    orient
    -0.07
    urez
    -0.07
    abend
    -0.07
    à¸IJาà¸Ļะ
    -0.07
    POSITIVE LOGITS
    åij½
    0.07
    å·´å¡ŀ
    0.07
    anda
    0.07
    è£ħ
    0.07
     câm
    0.07
    [--
    0.07
    ZE
    0.07
    "--
    0.07
    å°ij
    0.07
    çģ«é¾Ļ
    0.06
    Activations Density 0.923%

    No Known Activations