© 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. 22068
    Prev
    Next
    INDEX
    Explanations

    track something

    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
    ly
    -0.09
    volent
    -0.06
    etheless
    -0.06
    ified
    -0.06
    اÙĭ
    -0.06
    иÑĤÑĮÑģÑı
    -0.06
    éĢ¢
    -0.05
    imately
    -0.05
    ìį¨
    -0.05
    pszerű
    -0.05
    POSITIVE LOGITS
    dalena
    0.07
    ues
    0.07
    adata
    0.06
    es
    0.06
     prelim
    0.06
    ìĬ¤íĦ°
    0.06
    impi
    0.06
    immat
    0.06
    aversal
    0.06
    iên
    0.06
    Activations Density 0.015%

    No Known Activations