© 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. 18026
    Prev
    Next
    INDEX
    Explanations

    .com URLs or domains

    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
    oard
    -0.06
    isman
    -0.05
     surv
    -0.05
    odaw
    -0.05
    èįIJ
    -0.05
    ÙĥÙĩ
    -0.05
    endas
    -0.05
    į°
    -0.05
    æįİ
    -0.05
    ÙĥØ©
    -0.05
    POSITIVE LOGITS
    é
    0.06
    æ²³çķĶ
    0.06
    ste
    0.06
    oro
    0.05
    æĢİä¹ĪäºĨ
    0.05
    insel
    0.05
    vient
    0.05
    nern
    0.05
    åŁº
    0.05
    对äºİè¿ĻäºĽ
    0.05
    Activations Density 0.033%

    No Known Activations