© 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. 21470
    Prev
    Next
    INDEX
    Explanations

    optionalternative

    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
    Except
    -0.06
    idden
    -0.06
    udu
    -0.06
     pronunci
    -0.06
    ³³
    -0.05
    lear
    -0.05
    ÅĤac
    -0.05
    existe
    -0.05
     Except
    -0.05
    欢
    -0.05
    POSITIVE LOGITS
     option
    0.10
     Option
    0.09
    option
    0.09
    Option
    0.08
    -option
    0.08
    	option
    0.08
    éĢī项
    0.07
    .option
    0.07
    _option
    0.07
     alternative
    0.07
    Activations Density 0.301%

    No Known Activations