© 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. 22170
    Prev
    Next
    INDEX
    Explanations

    running out of

    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
    ç¨ĭ度çļĦ
    -0.05
    itto
    -0.05
    angelo
    -0.05
     statu
    -0.05
     ÙĦÙĪ
    -0.05
    εÏħ
    -0.05
    dert
    -0.05
    kup
    -0.05
    度ãģ®
    -0.05
    ç¨ĭ度ä¸Ĭ
    -0.05
    POSITIVE LOGITS
    ir
    0.06
    天æŶ
    0.06
    天çĦ¶
    0.06
    æł¹æį®åľ°
    0.06
    rek
    0.06
    ages
    0.06
    ×IJר
    0.06
    æļĸæļĸ
    0.05
    gev
    0.05
    ingen
    0.05
    Activations Density 0.012%

    No Known Activations