© 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. 18377
    Prev
    Next
    INDEX
    Explanations

    numbers and temperatures

    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
    wr
    -0.06
     déro
    -0.06
     récord
    -0.06
    osten
    -0.05
    리ìĬ¤
    -0.05
     Rehabil
    -0.05
    åıĪ大
    -0.05
    å°Ĭ享
    -0.05
     laps
    -0.05
    nga
    -0.05
    POSITIVE LOGITS
    à¹Ģลย
    0.06
    voer
    0.06
    пÑĥÑģк
    0.05
    íĥģ
    0.05
    ç®Ĺ
    0.05
     ÙĪات
    0.05
    åĩłä¸ĭ
    0.05
    adoo
    0.05
    luck
    0.05
    åĨľåİĨ
    0.05
    Activations Density 0.004%

    No Known Activations