© 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. 22011
    Prev
    Next
    INDEX
    Explanations

    location names

    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
    дие
    -0.06
    祺
    -0.06
    ë¡ł
    -0.06
    ÑĢÑĥм
    -0.06
    çīĪæĿĥä¸İåħį责声æĺİ
    -0.06
    æĢ§åıĬ
    -0.05
    вед
    -0.05
     fundamentally
    -0.05
     NotSupportedException
    -0.05
     célé
    -0.05
    POSITIVE LOGITS
     lahti
    0.05
    oso
    0.05
    urement
    0.05
    à¸Ĭà¹Īาà¸ĩ
    0.05
    enu
    0.05
    वार
    0.05
    alagi
    0.05
    our
    0.05
     setC
    0.05
    éĩijå±±
    0.05
    Activations Density 0.001%

    No Known Activations