© 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. 40178
    Prev
    Next
    INDEX
    Explanations

    approach, study, patients, query

    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
    ignant
    -0.06
    åĩ¡
    -0.06
     certainly
    -0.06
    å½ĵåľ°
    -0.06
    IDD
    -0.06
    åıijå¸ĥåħ¬åijĬ称
    -0.06
    olen
    -0.06
    ذر
    -0.06
    éĢļ
    -0.06
    å½ĵåħ¶
    -0.06
    POSITIVE LOGITS
    两天çļĦ
    0.08
    å¾·åįİ
    0.08
    this
    0.08
    æĪijçļĦå·¥ä½ľ
    0.08
    à¹Ģรืà¹Īà¸Ńà¸ĩà¸Ļีà¹ī
    0.08
    wier
    0.08
     proceedings
    0.08
    mert
    0.08
    å·¥ä½ľçļĦå¼Ģå±ķ
    0.08
    utherland
    0.08
    Activations Density 0.373%

    No Known Activations