© 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. 17207
    Prev
    Next
    INDEX
    Explanations

    who or for whom

    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
    egy
    -0.06
     Williamson
    -0.06
    èľ¿
    -0.06
    हर
    -0.06
     ÄĤ
    -0.06
    "class
    -0.05
    ensk
    -0.05
    ÙĩÙĨ
    -0.05
    ÙĨدÙĨ
    -0.05
     Lun
    -0.05
    POSITIVE LOGITS
    å¤ķ
    0.06
    æŃ£å¤Ħäºİ
    0.05
    лег
    0.05
    æŃ£åľ¨è¿Ľè¡Į
    0.05
    æĥ³çŁ¥éģĵ
    0.05
     current
    0.05
    ä½Ĩ缮åīį
    0.05
    é«ĺãĤģ
    0.05
     upcoming
    0.05
    éĤ£ç§į
    0.05
    Activations Density 0.073%

    No Known Activations