© 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. 61474
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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
    usercontent
    -0.08
    thouse
    -0.08
    _modified
    -0.08
    Ø·ÙĨ
    -0.07
    weet
    -0.07
    uby
    -0.07
    缸åħ³éĹ®çŃĶ
    -0.07
    jan
    -0.07
    anca
    -0.07
    è±Ĩçĵ£
    -0.07
    POSITIVE LOGITS
     respectively
    0.06
    æ£
    0.06
    æ®Ĭ
    0.06
    åį¡çī¹
    0.06
    èĪį
    0.06
    sometimes
    0.06
    åºĦæĿij
    0.06
    (PR
    0.06
    åįģä½Ļ
    0.06
    è°·
    0.05
    Activations Density 0.001%

    No Known Activations