© 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. 21522
    Prev
    Next
    INDEX
    Explanations

    code

    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
     Zub
    -0.05
    aray
    -0.05
     intimid
    -0.05
    à¸Ľà¸£à¸°à¸Īำ
    -0.05
    éħ°
    -0.05
    æĺİäºĨ
    -0.05
    usen
    -0.05
     confira
    -0.05
    æ·±éĢł
    -0.05
    å®ļåģļ
    -0.05
    POSITIVE LOGITS
    ober
    0.06
    à¸Ńà¸ģ
    0.06
    ITT
    0.06
    迹
    0.06
    comic
    0.06
    agne
    0.05
    ÙħاÙĨ
    0.05
    ODY
    0.05
    OTOR
    0.05
    ấp
    0.05
    Activations Density 0.012%

    No Known Activations