© 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. 19942
    Prev
    Next
    INDEX
    Explanations

    higher

    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
    ľ
    -0.05
    akra
    -0.05
    luv
    -0.05
    à¸Ĺาà¸ĩà¸ģาร
    -0.05
    ks
    -0.05
    話
    -0.05
    åıĸæļĸ
    -0.04
    æ¡Ī
    -0.04
    ÃŃp
    -0.04
     lapse
    -0.04
    POSITIVE LOGITS
    ancies
    0.06
    ahnya
    0.06
    å¼ĢçĿĢ
    0.06
    åİ»åIJ§
    0.06
     Ø´ÙĨا
    0.06
     Aroma
    0.06
    åħīèį£
    0.06
    SHOT
    0.06
    edin
    0.05
    illion
    0.05
    Activations Density 0.021%

    No Known Activations