© 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. 21387
    Prev
    Next
    INDEX
    Explanations

    now owns

    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
    itan
    -0.06
    лаг
    -0.05
     slightest
    -0.05
    Âł
    -0.05
    æ¯ıä¸Ģ件
    -0.05
    imin
    -0.05
    éļıç¼ĺ
    -0.05
     specifically
    -0.05
    严
    -0.05
    pan
    -0.05
    POSITIVE LOGITS
     qued
    0.06
    åī©
    0.06
    ä»ħ次äºİ
    0.06
     оÑģÑĤаÑĤ
    0.06
    _remaining
    0.06
    ãģ«æ®ĭ
    0.06
    å¿Į
    0.06
    åıªåī©ä¸ĭ
    0.06
    ÅŁt
    0.06
    åī©ä½ĻçļĦ
    0.06
    Activations Density 0.084%

    No Known Activations