© 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. 16920
    Prev
    Next
    INDEX
    Explanations

    initialise or initialize

    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
    åĸľéĹ»ä¹IJ
    -0.05
    è¥
    -0.05
    emo
    -0.05
    eno
    -0.05
     lots
    -0.05
     bew
    -0.05
    çĹħä¾ĭ
    -0.05
    estina
    -0.05
    åĭģ
    -0.05
    æŃĮ
    -0.04
    POSITIVE LOGITS
    åĪĿå§ĭ
    0.07
    æł¹
    0.07
    èµ·å§ĭ
    0.06
    æł¹çļĦ
    0.06
     initial
    0.06
    顶å±Ĥ
    0.06
    ÅĽmy
    0.06
     initialise
    0.06
    Initial
    0.06
    ulihan
    0.06
    Activations Density 0.023%

    No Known Activations