© 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. 18247
    Prev
    Next
    INDEX
    Explanations

    hexadecimal numbers like 0x

    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
    aleb
    -0.07
    ä¸Ģåıij
    -0.07
    alti
    -0.07
    bti
    -0.07
    tima
    -0.07
    trzyma
    -0.06
     dicks
    -0.06
     Confira
    -0.06
    åħĪæĿ¥
    -0.06
     provinciale
    -0.06
    POSITIVE LOGITS
    åģļçĿĢ
    0.05
    ignée
    0.05
     «
    0.05
    0.05
    ivre
    0.05
    ze
    0.05
    ake
    0.05
     ÑģÑĥ
    0.04
    æīĢè°ĵ
    0.04
     com
    0.04
    Activations Density 0.006%

    No Known Activations