© 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. 17418
    Prev
    Next
    INDEX
    Explanations

    recycling and trash programs

    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
     вп
    -0.06
    è·¨çķĮ
    -0.06
    lashes
    -0.06
    jev
    -0.06
    -generation
    -0.05
    ybers
    -0.05
    ç½®ä¹ĭ
    -0.05
    ASIL
    -0.05
    Born
    -0.05
    åį±æľº
    -0.05
    POSITIVE LOGITS
    пон
    0.06
    usz
    0.05
    æĭīå¼ĢäºĨ
    0.05
    åĪĨ项
    0.05
    åĪĨåĮº
    0.05
    åĪĨç±»
    0.05
    ccc
    0.05
     segreg
    0.05
    åĪĨæ¸ħ
    0.05
    caf
    0.05
    Activations Density 0.011%

    No Known Activations