© 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. 18388
    Prev
    Next
    INDEX
    Explanations

    question or problem

    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
    ogo
    -0.08
    OGO
    -0.08
    ãģĭãģ®
    -0.07
     thereafter
    -0.07
    asi
    -0.07
    è·¯ä¸ĬçļĦ
    -0.07
    assen
    -0.07
    asse
    -0.07
    å¹³åľ°
    -0.07
    asio
    -0.07
    POSITIVE LOGITS
     question
    0.09
    èIJį
    0.07
    è¦ģæ±Ĥåľ¨
    0.07
    éĹ®é¢ĺ
    0.07
    Question
    0.07
     вопÑĢоÑģ
    0.07
     Question
    0.07
     problem
    0.07
    oret
    0.07
     Frage
    0.07
    Activations Density 0.001%

    No Known Activations