© 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. 20704
    Prev
    Next
    INDEX
    Explanations

    listing others

    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
    elling
    -0.06
    à¸Ļà¹Į
    -0.06
    uring
    -0.06
    aneous
    -0.06
    anes
    -0.06
    tes
    -0.06
    ten
    -0.06
    ä¸įäºĨ
    -0.06
    anie
    -0.06
    accord
    -0.05
    POSITIVE LOGITS
    mensagem
    0.06
    chie
    0.06
    ifice
    0.06
    оÑĤе
    0.06
    kön
    0.06
    YYY
    0.05
    åĥ»
    0.05
    edet
    0.05
     repeated
    0.05
    built
    0.05
    Activations Density 0.008%

    No Known Activations