© 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. 61829
    Prev
    Next
    INDEX
    Explanations

    verbs of reporting speech

    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
    avy
    -0.09
    ارد
    -0.08
    avu
    -0.07
     scre
    -0.07
    ÎŃÏģγ
    -0.07
    Err
    -0.07
    ä¸ªå·¥ä½ľ
    -0.07
    çģŃ
    -0.07
    æľī以ä¸ĭ
    -0.07
    StatusCode
    -0.07
    POSITIVE LOGITS
    çĮĽ
    0.07
    课æŶ
    0.07
    æĽ¦
    0.07
     بÙĨدÛĮ
    0.06
     dikutip
    0.06
    aily
    0.06
    翼翼
    0.06
    ä½
    0.06
    .pb
    0.06
    ÙĨدÙĩ
    0.06
    Activations Density 0.143%

    No Known Activations