© 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. 17514
    Prev
    Next
    INDEX
    Explanations

    credentials supplied

    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
    çªĥ
    -0.06
    éŀ
    -0.06
    etch
    -0.06
    åĨ¶
    -0.06
    urses
    -0.06
    ide
    -0.06
    æ¾Ī
    -0.05
    enders
    -0.05
    anda
    -0.05
    -sided
    -0.05
    POSITIVE LOGITS
     conc
    0.06
    ¯
    0.05
    Ãłnh
    0.05
    éĢļåĬĽ
    0.05
    å¸ļ
    0.05
    èµĦæĸĻ
    0.05
    åIJĮå¿ĥ
    0.05
     marshal
    0.05
    ÙĨÙĬ
    0.05
     [_
    0.05
    Activations Density 0.033%

    No Known Activations