© 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. 12121
    Prev
    Next
    INDEX
    Explanations

    `requestCode`, `method`, `.Field`, `Type`

    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
     tip
    -0.07
    å¨Ĩ
    -0.07
     enn
    -0.07
    ellino
    -0.06
    æĸ°æĹ¶ä»£ä¸ŃåĽ½çī¹èī²ç¤¾ä¼ļ主ä¹ī
    -0.06
    ä¹Łä¼ļæľī
    -0.06
    ardi
    -0.06
    ä¹ŁæĽ´åĬł
    -0.06
     ÙģÙĨ
    -0.06
    æ¤
    -0.06
    POSITIVE LOGITS
    ä¸įå¹²
    0.08
    ủ
    0.08
    çŁ¢
    0.07
    ikian
    0.07
    .shift
    0.07
    aires
    0.07
    çĶ¨å¿ĥ
    0.07
    _HERE
    0.07
    UNE
    0.07
    zee
    0.07
    Activations Density 0.006%

    No Known Activations