© 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. 20569
    Prev
    Next
    INDEX
    Explanations

    assignment operators

    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
    ly
    -0.05
    iet
    -0.05
     -
    -0.05
     i
    -0.05
     é
    -0.05
    ed
    -0.05
    -s
    -0.05
    _b
    -0.05
    h
    -0.05
    ie
    -0.05
    POSITIVE LOGITS
    kope
    0.07
    (Cs
    0.07
    رÙĩا
    0.07
    λί
    0.07
    åŃIJãģķãĤĵ
    0.06
     Ukra
    0.06
    ÏĢÏī
    0.06
    uses
    0.06
    iksi
    0.06
    mata
    0.06
    Activations Density 0.011%

    No Known Activations