© 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. 14572
    Prev
    Next
    INDEX
    Explanations

    question marks and commas

    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
    orph
    -0.07
    oom
    -0.06
    »
    -0.06
    inho
    -0.06
    rats
    -0.06
    ات
    -0.06
    Ã¶ÃŁen
    -0.06
    ostas
    -0.06
    cores
    -0.05
    Ùİات
    -0.05
    POSITIVE LOGITS
    åıĸåĨ³äºİ
    0.08
    ire
    0.08
    ate
    0.08
    ij¸
    0.08
    æ¶īåıĬåĪ°
    0.08
    legate
    0.07
    åħ´åįİ
    0.07
    ãĥIJãĥ¼ãĤ¸
    0.07
    IONAL
    0.07
    ocu
    0.07
    Activations Density 0.573%

    No Known Activations