© 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. 17659
    Prev
    Next
    INDEX
    Explanations

    I know, I uploaded, My name

    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
    éŃĶå¹»
    -0.07
    bote
    -0.06
    antic
    -0.06
    arbet
    -0.06
    第ä¸ĢçĻ¾ä¸ĥ
    -0.06
    à¹Ģà¸ĸà¸Ńะ
    -0.06
    ovac
    -0.06
    ation
    -0.06
    .isNullOrEmpty
    -0.06
    zonder
    -0.06
    POSITIVE LOGITS
    immen
    0.05
    appel
    0.05
    ja
    0.05
    im
    0.05
     pere
    0.05
    CLI
    0.05
    look
    0.05
    ê°ģ
    0.05
    sel
    0.05
    лак
    0.05
    Activations Density 0.001%

    No Known Activations