© 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. 18086
    Prev
    Next
    INDEX
    Explanations

    database and data storage

    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
    abay
    -0.06
    çĶŁç´ł
    -0.05
    å¼ĢçıŃ
    -0.05
    defaults
    -0.05
     Jaw
    -0.05
     müh
    -0.05
    à¹Ģà¸Ľà¸¥à¹Īา
    -0.05
     scrapy
    -0.05
    idious
    -0.05
     defaults
    -0.05
    POSITIVE LOGITS
    onta
    0.06
     consoles
    0.06
     concept
    0.06
    æ¦Ĥ念
    0.06
    ayan
    0.05
    æĪIJç»©æŁ¥è¯¢
    0.05
    elum
    0.05
    uban
    0.05
    æıı
    0.05
    à®®à¯Ī
    0.05
    Activations Density 0.014%

    No Known Activations