© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20255
    Prev
    Next
    INDEX
    Explanations

    detecting non-english characters

    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
    åİļ
    -0.05
    çĽ²
    -0.05
    ely
    -0.05
    åIJŀ
    -0.05
    å¢Ļ
    -0.05
    heen
    -0.05
    常æľī
    -0.05
     Bris
    -0.05
    DU
    -0.05
    ita
    -0.05
    POSITIVE LOGITS
    atter
    0.07
    ahren
    0.06
    æ¸ħæ¥ļ
    0.06
    讲çļĦæĺ¯
    0.06
    ξι
    0.06
    alis
    0.06
    bourne
    0.06
    ίαÏĤ
    0.06
    instanc
    0.06
    ิà¹Īà¸ĩ
    0.06
    Activations Density 0.010%

    No Known Activations