© 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. 21548
    Prev
    Next
    INDEX
    Explanations

    code initialization

    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
    igr
    -0.05
    ifest
    -0.05
     long
    -0.05
    åħ¨æ°ijåģ¥èº«
    -0.05
    çľĭä¸įè§ģ
    -0.05
    former
    -0.05
    i
    -0.05
     suite
    -0.05
     n
    -0.05
    ve
    -0.05
    POSITIVE LOGITS
     modele
    0.06
    amica
    0.06
    åĴĮåĪ«äºº
    0.06
    leiÃŁ
    0.06
    epy
    0.06
     kurv
    0.06
    ÙĩÙĪرÙĬ
    0.06
    ën
    0.06
    dessous
    0.06
     Auss
    0.06
    Activations Density 0.008%

    No Known Activations