© 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. 16337
    Prev
    Next
    INDEX
    Explanations

    alright or right followed by comma or so

    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
    ation
    -0.10
    reiro
    -0.08
    occhio
    -0.07
    æĭīæĭī
    -0.07
    åĨīåĨī
    -0.07
    ä¹ĭæģĭ
    -0.07
    ugno
    -0.07
    ized
    -0.07
    reek
    -0.07
    reira
    -0.06
    POSITIVE LOGITS
    ت
    0.09
    تاÙĨ
    0.08
    er
    0.08
    eens
    0.08
    een
    0.08
    sver
    0.08
    eous
    0.08
    ا
    0.08
    ties
    0.08
    à¦ĩ
    0.08
    Activations Density 0.003%

    No Known Activations