© 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. 20515
    Prev
    Next
    INDEX
    Explanations

    @rem, mpi, special 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
    epend
    -0.06
     rodzaju
    -0.06
    uration
    -0.05
    çŁ£
    -0.05
    thur
    -0.05
     Intr
    -0.05
    á»Ļm
    -0.05
     caisse
    -0.05
    åıĬæŶå¤ĦçIJĨ
    -0.05
    alas
    -0.05
    POSITIVE LOGITS
     اÙĦÙĩد
    0.06
     tern
    0.05
     terrestre
    0.05
    åĽłäºº
    0.05
     res
    0.05
    tps
    0.05
    ÑĤеÑĤ
    0.05
    ìļ°
    0.05
    decess
    0.05
    åĴĮä¸ī
    0.05
    Activations Density 0.009%

    No Known Activations