© 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. 21678
    Prev
    Next
    INDEX
    Explanations

    L

    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
    Ñģий
    -0.06
     mys
    -0.06
    ÄĻd
    -0.06
    uhu
    -0.06
    éro
    -0.06
    rodu
    -0.06
    gian
    -0.06
    à¹Ģà¸Īà¸Ļ
    -0.06
    stice
    -0.05
     Wsp
    -0.05
    POSITIVE LOGITS
    åħ¨åĽ½çļĦ
    0.05
    alia
    0.05
    è§Ĩè§īæķĪæŀľ
    0.05
    Ùĭ
    0.05
    åħ¶ä¸Ń
    0.05
    夫人
    0.05
    endienst
    0.05
    Õ¡Õ´
    0.05
    è§Ĩè§īä¸Ĭ
    0.05
    ne
    0.05
    Activations Density 0.004%

    No Known Activations