© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19119
    Prev
    Next
    INDEX
    Explanations

    GPU

    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
    s
    -0.09
    dirs
    -0.05
    CLA
    -0.05
    icon
    -0.05
    down
    -0.05
    ä¸Ģ个人
    -0.05
     дело
    -0.05
    Ñĭ
    -0.05
    åıijè¾¾
    -0.05
    ات
    -0.05
    POSITIVE LOGITS
    ierce
    0.08
    ehm
    0.08
    ever
    0.07
    bant
    0.07
    ndan
    0.06
    ем
    0.06
    epsi
    0.06
    akest
    0.06
    ë§ĪìŀIJ
    0.06
    éĩĩåıĸæݪæĸ½
    0.06
    Activations Density 0.002%

    No Known Activations