© 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. 20218
    Prev
    Next
    INDEX
    Explanations

    social, culture, terms, nature

    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
    ³
    -0.06
    achinery
    -0.05
    æľºåĴĮ
    -0.05
    essel
    -0.05
    ,
    -0.05
    ward
    -0.05
    åĴĮæľīåħ³
    -0.05
    Å©
    -0.05
    -run
    -0.05
     hers
    -0.05
    POSITIVE LOGITS
    azit
    0.07
    èĩªèº«
    0.06
    epen
    0.06
    azos
    0.06
    ovem
    0.06
    usse
    0.06
    thane
    0.06
    ceo
    0.06
    _collections
    0.06
     beis
    0.06
    Activations Density 0.025%

    No Known Activations