© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22285
    Prev
    Next
    INDEX
    Explanations

    service related to application

    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
    ÑĦикаÑĨиÑı
    -0.06
     vong
    -0.06
     ÑĪÑĤÑĥка
    -0.06
    unner
    -0.06
    bane
    -0.06
    çļĦéĺ¶æ®µ
    -0.06
    andi
    -0.06
    unden
    -0.06
    çļĦä¾Ŀæį®
    -0.06
     sometimes
    -0.06
    POSITIVE LOGITS
    iller
    0.06
    ain
    0.06
    olat
    0.06
    èo
    0.05
    å®ĥèĥ½
    0.05
    äºĮä¸Ń
    0.05
    aker
    0.05
    endez
    0.05
    å®ĥä¸İ
    0.05
    o
    0.05
    Activations Density 0.001%

    No Known Activations