© 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. 21062
    Prev
    Next
    INDEX
    Explanations

    filler, fluids, molecules, materials

    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
     Donner
    -0.06
    åĴĮæľīåħ³
    -0.06
    游åĩ»
    -0.06
    idel
    -0.06
    åħħåĪĨèĢĥèĻij
    -0.06
     autof
    -0.06
    fahr
    -0.06
    irem
    -0.06
    åIJ¬åıĸäºĨ
    -0.06
    achtung
    -0.05
    POSITIVE LOGITS
    ä¾Ŀ
    0.06
    éľĢæ±Ĥ
    0.06
     liquids
    0.06
    çŃĶ
    0.06
     need
    0.05
     fluids
    0.05
    åij¼ãģ³
    0.05
     каб
    0.05
    еÑĩÑĮ
    0.05
    è¯Ńç§į
    0.05
    Activations Density 0.038%

    No Known Activations