© 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. 17195
    Prev
    Next
    INDEX
    Explanations

    This COURT

    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
    å¤į
    -0.06
     I
    -0.06
    -
    -0.06
     cor
    -0.05
    II
    -0.05
    err
    -0.05
     m
    -0.05
    I
    -0.05
     meny
    -0.05
     hic
    -0.05
    POSITIVE LOGITS
    Å¡n
    0.07
    /stretch
    0.07
    æĤį
    0.07
    åĨįçĤ¹åĩ»
    0.06
    å·´å·´
    0.06
    _ty
    0.06
    åºĶçĶ¨åľ¨
    0.06
    kira
    0.06
    Tunes
    0.06
    ĥģ
    0.06
    Activations Density 0.001%

    No Known Activations