© 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. 17113
    Prev
    Next
    INDEX
    Explanations

    free software Foundation

    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
    ling
    -0.05
    صب
    -0.05
    oya
    -0.05
     assets
    -0.05
    çĹ´
    -0.05
     structures
    -0.05
    unt
    -0.05
    ä¸Ńç«ĭ
    -0.05
    lsa
    -0.05
    Est
    -0.04
    POSITIVE LOGITS
    移è¡Į
    0.06
    iskan
    0.06
    Äįk
    0.06
    оÑģÑĮ
    0.06
    idla
    0.06
    ometri
    0.06
    replacement
    0.06
    èĻ«çĹħ
    0.06
    ¨
    0.06
    ç»Ĵ
    0.06
    Activations Density 0.060%

    No Known Activations