© 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. 22053
    Prev
    Next
    INDEX
    Explanations

    behaviour of

    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
    ware
    -0.05
    ism
    -0.05
    ed
    -0.05
    ists
    -0.05
    èĢĮå·²
    -0.05
    uns
    -0.05
    re
    -0.05
     incidental
    -0.05
    lord
    -0.05
    tw
    -0.05
    POSITIVE LOGITS
    æ½°
    0.07
    zugehen
    0.07
    ç³»ç»Łè¿Ľè¡Į
    0.07
    toj
    0.07
    ffici
    0.06
    -shadow
    0.06
    æĢ§èĥ½åĴĮ
    0.06
    agli
    0.06
    float
    0.06
     ÑģÑĤиÑħ
    0.06
    Activations Density 0.015%

    No Known Activations