© 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. 21177
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
     millennia
    -0.06
    inston
    -0.06
    ennen
    -0.06
    åłĨ
    -0.06
    ptom
    -0.06
    gem
    -0.06
    强åĮĸ
    -0.05
    便å°Ĩ
    -0.05
    odus
    -0.05
    osse
    -0.05
    POSITIVE LOGITS
    æŃ»æ´»
    0.06
    umatic
    0.06
    æľī计åĪĴ
    0.05
     Ñĥго
    0.05
     Ñĥг
    0.05
    неÑĤа
    0.05
    å°Ħ
    0.05
    è¿ŀ带
    0.05
     Ang
    0.05
    æľīæĦıåIJij
    0.05
    Activations Density 0.005%

    No Known Activations