© 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. 17971
    Prev
    Next
    INDEX
    Explanations

    asking questions

    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
    ä½ľä¸ºä¸Ģ个
    -0.06
    åħ¨ä¼ļç²¾ç¥ŀ
    -0.05
    æİł
    -0.05
     voici
    -0.05
    .div
    -0.05
     loaf
    -0.05
     énorm
    -0.05
    ichni
    -0.05
    дÑĭÒĽ
    -0.05
    ÑĢеÑĤ
    -0.05
    POSITIVE LOGITS
    er
    0.07
    عاÙĨ
    0.06
    eroy
    0.06
    cita
    0.06
    arez
    0.06
    taj
    0.06
    enda
    0.06
    ÙĦÙĬÙĨ
    0.06
     allá
    0.05
     awhile
    0.05
    Activations Density 0.006%

    No Known Activations