© 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. 18526
    Prev
    Next
    INDEX
    Explanations

    grumpy

    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
    æīĵå¾Ĺ
    -0.06
    borne
    -0.06
    abia
    -0.06
    รà¹Īวมà¸ģัà¸Ļ
    -0.05
    鸳
    -0.05
    å¼¹
    -0.05
    hole
    -0.05
    enant
    -0.05
    ÏīÏĤ
    -0.05
    olutely
    -0.05
    POSITIVE LOGITS
    blad
    0.06
    _kw
    0.05
    幸
    0.05
    æķĸ
    0.05
    åĽ¢éĺŁæĪIJåijĺ
    0.05
     bando
    0.05
     dobro
    0.05
    sorting
    0.05
     Genome
    0.05
    ylim
    0.05
    Activations Density 0.001%

    No Known Activations