© 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. 17427
    Prev
    Next
    INDEX
    Explanations

    language learning and translation

    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
    னà¯į
    -0.05
     less
    -0.05
    O
    -0.05
    è¡Į为
    -0.05
    è´¹
    -0.05
     sahi
    -0.05
    å¾ģ
    -0.04
    åŁł
    -0.04
    riel
    -0.04
    à¹Ĥà¸ķ
    -0.04
    POSITIVE LOGITS
    unk
    0.06
     Patr
    0.06
    çļĦåĪ¶ä½ľæĸ¹æ³ķ
    0.06
     }):
    0.06
    neze
    0.06
    .translate
    0.06
     translations
    0.06
    reas
    0.06
    åĽĽæĸ¹
    0.06
    éĩįè¦ģçļĦæĺ¯
    0.06
    Activations Density 0.005%

    No Known Activations