© 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. 61758
    Prev
    Next
    INDEX
    Explanations

    learning algorithms

    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
    ostal
    -0.07
     specimen
    -0.06
    ansom
    -0.06
    æĹ¢ä¸į
    -0.06
    ä¸Ģ空
    -0.06
    樱
    -0.06
     Hug
    -0.06
     disposed
    -0.06
     staff
    -0.06
    åĢĶ强
    -0.06
    POSITIVE LOGITS
     randomized
    0.14
     advers
    0.09
     Breitbart
    0.09
    éĩijæ¡¥
    0.09
    yscale
    0.09
    对æĬĹ
    0.09
    á»ĩu
    0.08
    -random
    0.08
     Jain
    0.08
     adversary
    0.08
    Activations Density 0.067%

    No Known Activations