© 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. 22128
    Prev
    Next
    INDEX
    Explanations

    validate input and data

    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
    teenth
    -0.07
    MOTE
    -0.06
    rys
    -0.06
    нÑı
    -0.06
    ched
    -0.06
    deaux
    -0.06
    hias
    -0.06
    lass
    -0.06
    ÑĤен
    -0.06
    ero
    -0.06
    POSITIVE LOGITS
    a
    0.06
    e
    0.06
    eded
    0.06
    çŁ¥
    0.06
    Ø©
    0.06
    æѤæŶ
    0.06
    ed
    0.06
    ele
    0.06
    veni
    0.05
    equ
    0.05
    Activations Density 0.008%

    No Known Activations