© 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. 40866
    Prev
    Next
    INDEX
    Explanations

    spelling

    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
    sama
    -0.08
    oy
    -0.08
    导åĩº
    -0.07
    ouncements
    -0.07
    ROLE
    -0.07
    kers
    -0.07
    γÏĩ
    -0.07
    çĶ³æĺİ
    -0.07
    zej
    -0.07
    æĶ¯æŁ±
    -0.06
    POSITIVE LOGITS
     spelling
    0.15
     spell
    0.13
    spell
    0.12
     Spells
    0.10
     spells
    0.10
     phon
    0.10
     Spell
    0.10
     spelled
    0.09
    åŃĹå½¢
    0.09
    æĭ¼
    0.09
    Activations Density 0.052%

    No Known Activations