© 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. 21200
    Prev
    Next
    INDEX
    Explanations

    jokes, scandal, article, stimulates, market

    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
     Purtroppo
    -0.08
    央
    -0.07
    erja
    -0.07
    towe
    -0.07
     Ovviamente
    -0.07
    ừ
    -0.07
     favori
    -0.07
    izon
    -0.07
    -wife
    -0.06
    ç´°ç¯Ģ
    -0.06
    POSITIVE LOGITS
    ess
    0.05
     r
    0.05
     mol
    0.05
     attempts
    0.05
     under
    0.05
    re
    0.05
    ine
    0.05
     subject
    0.05
     m
    0.05
     :
    0.05
    Activations Density 0.002%

    No Known Activations