© 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. 21141
    Prev
    Next
    INDEX
    Explanations

    technical terms and definitions

    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
     inspir
    -0.07
    azionale
    -0.06
    /fw
    -0.06
    itaria
    -0.06
    ç¦į
    -0.05
    Insp
    -0.05
    ucking
    -0.05
     Inspired
    -0.05
    ivio
    -0.05
     hammered
    -0.05
    POSITIVE LOGITS
    B
    0.06
    æľªç»ı
    0.06
    ez
    0.06
     without
    0.05
    ordu
    0.05
    onc
    0.05
    ifi
    0.05
    un
    0.05
     neatly
    0.05
     shorthand
    0.05
    Activations Density 0.008%

    No Known Activations