© 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. 18045
    Prev
    Next
    INDEX
    Explanations

    mathematical formula structures

    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
    vah
    -0.06
    ãĥŃãĤ¹
    -0.06
     anomal
    -0.06
    举åįĩ
    -0.05
    ä¸įæĮī
    -0.05
    å°ĶèĴĻ
    -0.05
    rouch
    -0.05
    ader
    -0.05
    å¾ij
    -0.05
    oller
    -0.05
    POSITIVE LOGITS
     Merge
    0.06
     merging
    0.06
     Keg
    0.05
     merged
    0.05
    èŀįåIJĪ
    0.05
     merge
    0.05
     merges
    0.05
    merge
    0.05
    åIJĪ并
    0.05
     distinc
    0.05
    Activations Density 0.021%

    No Known Activations