© 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. 16949
    Prev
    Next
    INDEX
    Explanations

    dependent source

    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
    ostro
    -0.06
     aangeboden
    -0.06
    åıĮåĩı
    -0.05
     compar
    -0.05
     variance
    -0.05
    å¿ĺä¸įäºĨ
    -0.05
    utam
    -0.05
    äºĤ
    -0.05
    èĹ¥
    -0.05
     плаÑĤÑĦоÑĢма
    -0.05
    POSITIVE LOGITS
    ichte
    0.06
    orks
    0.06
    ork
    0.06
    vec
    0.06
     vector
    0.06
    Vec
    0.05
    ç¼Ŀ
    0.05
     looping
    0.05
    é«ĺå¯Ĩ度
    0.05
    å¸IJ
    0.05
    Activations Density 0.007%

    No Known Activations