© 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. 63937
    Prev
    Next
    INDEX
    Explanations

    matrix factorization, decomposition, splitting

    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
    wing
    -0.07
    æĭĤ
    -0.06
    ä»ģ
    -0.06
    èŁ
    -0.06
    èģ
    -0.06
    讼
    -0.06
    åĬĽæīĢèĥ½åıĬ
    -0.06
    åĪĨ享åĪ°æľĭåıĭåľĪ
    -0.06
    æ¸ħèĦĨ
    -0.06
    å±ħæ°ij
    -0.06
    POSITIVE LOGITS
    æ©
    0.08
    orza
    0.07
    engen
    0.07
    éŁŃ
    0.07
    Ñģло
    0.07
    港åĮº
    0.07
    :image
    0.07
    ensee
    0.07
    æ³ķçŃī
    0.07
     Saber
    0.07
    Activations Density 0.008%

    No Known Activations