© 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. 18059
    Prev
    Next
    INDEX
    Explanations

    check with instructions

    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
    utos
    -0.06
    czy
    -0.06
    Ú©Ø´
    -0.05
    ÙģÙĩ
    -0.05
     бÑĥ
    -0.05
     Amen
    -0.05
    анда
    -0.05
    _smooth
    -0.05
    cw
    -0.05
    çªģ
    -0.05
    POSITIVE LOGITS
    leps
    0.05
     scarc
    0.05
    å®ŀæĻ¯
    0.05
    å®ŀéĻħä¸Ĭæĺ¯
    0.05
    oby
    0.05
     zac
    0.05
    лива
    0.05
    å®ŀæĻ¯åĽ¾
    0.05
    實éļĽä¸Ĭ
    0.05
    åĪ°ä¸ĭ
    0.05
    Activations Density 0.008%

    No Known Activations