© 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. 21912
    Prev
    Next
    INDEX
    Explanations

    promote health benefits

    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
    ä¹ı
    -0.07
     sensed
    -0.06
     Shark
    -0.05
    &apos
    -0.05
    elia
    -0.05
     sensing
    -0.05
     Duffy
    -0.05
     sense
    -0.05
    IFI
    -0.05
    eeper
    -0.05
    POSITIVE LOGITS
    ongo
    0.06
     coats
    0.06
    imi
    0.05
     formul
    0.05
    _creation
    0.05
     Formul
    0.05
    listing
    0.05
    ÑĭÑĢ
    0.05
     Auc
    0.05
     عÙħÙĦ
    0.05
    Activations Density 0.008%

    No Known Activations