© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19162
    Prev
    Next
    INDEX
    Explanations

    eigenvectors and basis functions

    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
    apun
    -0.06
    oland
    -0.06
    åĽŀè¿ĩç¥ŀ
    -0.06
    гноз
    -0.05
    ä¹ĭèī²
    -0.05
    entries
    -0.05
    ê´Ħ
    -0.05
    keh
    -0.05
     cast
    -0.05
     appre
    -0.05
    POSITIVE LOGITS
    reen
    0.06
    ifty
    0.06
     utility
    0.06
     helper
    0.05
    åħ¬çĶ¨
    0.05
     شع
    0.05
    -helper
    0.05
    æ»´æ°´
    0.05
     Utility
    0.05
     orthogonal
    0.05
    Activations Density 0.056%

    No Known Activations