© 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. 28370
    Prev
    Next
    INDEX
    Explanations

    criteria, remote, results, itch, care, dynamic

    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
    igas
    -0.08
    ||||
    -0.07
    Means
    -0.07
    igi
    -0.06
     ÑģквозÑĮ
    -0.06
    æļĤè¡Į
    -0.06
    iting
    -0.06
    -decoration
    -0.06
    宫
    -0.06
     Diante
    -0.06
    POSITIVE LOGITS
     <+
    0.08
    éŃ
    0.07
     Ñĥни
    0.07
    æķĻ书
    0.07
    throp
    0.06
    ä»įçĦ¶æĺ¯
    0.06
    ackers
    0.06
     versatile
    0.06
    é³Ħ
    0.06
    åħį责声æĺİ
    0.06
    Activations Density 0.478%

    No Known Activations