© 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. 22026
    Prev
    Next
    INDEX
    Explanations

    extracting ids/data from markup

    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
    ä¸Ģå®ļ
    -0.06
    P
    -0.05
     R
    -0.05
    æĺ§
    -0.05
     P
    -0.05
    ema
    -0.05
    us
    -0.05
    p
    -0.05
    iram
    -0.05
     marks
    -0.05
    POSITIVE LOGITS
    uret
    0.07
     Drit
    0.06
    леÑĤниÑħ
    0.06
    åݻ年åºķ
    0.06
    arten
    0.06
    ijen
    0.06
    foro
    0.06
     phán
    0.06
    éķ¿æľŁåĿļæĮģ
    0.06
    oze
    0.06
    Activations Density 0.059%

    No Known Activations