© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17756
    Prev
    Next
    INDEX
    Explanations

    specifies quantity or time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    à¸Ī
    -0.06
    ä»»
    -0.06
     Practice
    -0.06
     hinted
    -0.05
    Run
    -0.05
    bürger
    -0.05
    odne
    -0.05
     Runs
    -0.05
    run
    -0.05
    Practice
    -0.05
    POSITIVE LOGITS
    äºĨå¤ļå°ij
    0.07
    æľīå¤ļå°ij
    0.06
    instead
    0.06
     specifies
    0.06
     instead
    0.06
    å¤ļå°ijéĴ±
    0.06
    Specifies
    0.06
     describes
    0.06
    ова
    0.06
    acker
    0.06
    Activations Density 0.108%

    No Known Activations