© 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. 18647
    Prev
    Next
    INDEX
    Explanations

    package lists; translation type

    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
    orgeous
    -0.07
    åĢ¼å¾ĹæľŁå¾ħ
    -0.07
    åľ¨åİ¿
    -0.07
    ØŃاÙģظة
    -0.07
    çħ§
    -0.07
    erokee
    -0.06
     presenci
    -0.06
     Idéal
    -0.06
     olaraq
    -0.06
    esso
    -0.06
    POSITIVE LOGITS
    [
    0.06
    å®ī
    0.05
    åĨħåľ¨
    0.05
    (
    0.05
     extr
    0.05
    «
    0.04
    zio
    0.04
     Ehren
    0.04
     «
    0.04
    untas
    0.04
    Activations Density 0.002%

    No Known Activations