© 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. 20865
    Prev
    Next
    INDEX
    Explanations

    common

    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
    ButtonItem
    -0.06
    istou
    -0.06
    ÚĺÛĮ
    -0.06
    Indented
    -0.06
    вÑĭÑĩай
    -0.06
     casc
    -0.06
    geld
    -0.06
    ingang
    -0.06
     gratu
    -0.06
    alu
    -0.06
    POSITIVE LOGITS
    æľŁ
    0.05
     Harmon
    0.05
    èĢĮç«ĭ
    0.05
    harmon
    0.05
    lo
    0.05
     Tart
    0.05
    Min
    0.05
    eyer
    0.05
    çĶŁæł¹
    0.05
     Minimum
    0.05
    Activations Density 0.014%

    No Known Activations