© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19572
    Prev
    Next
    INDEX
    Explanations

    slow performance or processes

    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
    laÄį
    -0.06
    antin
    -0.06
    ween
    -0.06
    orial
    -0.06
    .fromJson
    -0.05
    seit
    -0.05
    igen
    -0.05
    nière
    -0.05
    imentary
    -0.05
    ÙĬرÙĬØ©
    -0.05
    POSITIVE LOGITS
    blo
    0.07
    à¹ģà¸ĸว
    0.06
    zzo
    0.06
    à¸Ħà¹īา
    0.06
    æľ¯
    0.06
     blo
    0.05
    ones
    0.05
    ev
    0.05
    ietro
    0.05
    enda
    0.05
    Activations Density 0.013%

    No Known Activations