© 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. 17833
    Prev
    Next
    INDEX
    Explanations

    from ... to

    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
    anner
    -0.06
    na
    -0.05
    каÑģ
    -0.05
    "All
    -0.05
    -all
    -0.05
    mot
    -0.05
    第ä¸īçĻ¾
    -0.05
    anggapi
    -0.05
    è¿Ļå°ı
    -0.05
    pcl
    -0.05
    POSITIVE LOGITS
    itti
    0.06
    žd
    0.06
    åŃ£
    0.06
     binge
    0.06
    éķ¿éĢĶ
    0.05
     Ùħبت
    0.05
    åİ»è´Ńä¹°
    0.05
    oday
    0.05
     Ùħرت
    0.05
    vik
    0.05
    Activations Density 0.011%

    No Known Activations