© 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. 17333
    Prev
    Next
    INDEX
    Explanations

    configuration and technical terms

    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
     **.**
    -0.07
     **:
    -0.07
     **:**
    -0.07
    è¿Ľè¡ĮæŶ
    -0.07
    æİĤ
    -0.07
    çĪ±çļĦ人
    -0.07
    æĴĩ
    -0.06
    ermen
    -0.06
    ETERS
    -0.06
     webshop
    -0.06
    POSITIVE LOGITS
     +
    0.06
    urt
    0.06
     [
    0.05
     L
    0.05
    urs
    0.05
     nan
    0.05
     /
    0.05
     Laure
    0.05
     T
    0.05
     apt
    0.05
    Activations Density 0.025%

    No Known Activations