© 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. 19805
    Prev
    Next
    INDEX
    Explanations

    claimants

    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
    chet
    -0.06
    werb
    -0.06
     Transit
    -0.06
    ÙĦÙģØ©
    -0.06
    ertz
    -0.06
    ilent
    -0.05
     terc
    -0.05
    chette
    -0.05
     atop
    -0.05
    赫å°Ķ
    -0.05
    POSITIVE LOGITS
     valor
    0.06
    æģ¤
    0.06
    ore
    0.05
    çIJĨèµĶ
    0.05
    DEC
    0.05
    burse
    0.05
     rehabilit
    0.05
    ä»·åĢ¼çļĦ
    0.05
    åħĦå¼Łä»¬
    0.05
    awn
    0.05
    Activations Density 0.021%

    No Known Activations