© 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. 17847
    Prev
    Next
    INDEX
    Explanations

    Milk

    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
    eer
    -0.09
    isons
    -0.08
    undi
    -0.07
    دد
    -0.07
    iq
    -0.06
    zo
    -0.06
    oz
    -0.06
    åºŀ
    -0.06
    ez
    -0.06
    oj
    -0.06
    POSITIVE LOGITS
    ly
    0.07
    æľŁçļĦ
    0.06
    combe
    0.06
    teau
    0.06
    western
    0.06
    room
    0.06
    ÅĤa
    0.06
    efois
    0.06
    à¸Ĭีà¸ŀ
    0.06
    loe
    0.06
    Activations Density 0.004%

    No Known Activations