© 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. 18012
    Prev
    Next
    INDEX
    Explanations

    been recorded, loaded, manufactured, removed

    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
     Especially
    -0.06
    mena
    -0.06
    å°¤åħ¶
    -0.06
    éĴŀ
    -0.06
    weise
    -0.06
     à¹Ĩ
    -0.06
     especially
    -0.05
    biot
    -0.05
    åıijçļĦ
    -0.05
    Ù°
    -0.05
    POSITIVE LOGITS
    شاÙĨ
    0.06
    ä¸ĩäºĭ
    0.05
    eer
    0.05
    atorial
    0.05
    iron
    0.05
    formed
    0.05
    ayer
    0.05
    hers
    0.05
    å°ļåľ¨
    0.05
    িয়à§ĩ
    0.05
    Activations Density 0.064%

    No Known Activations