© 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. 21593
    Prev
    Next
    INDEX
    Explanations

    advice and 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
    人为
    -0.06
    è¿ĩå¤ļ
    -0.05
     laboratory
    -0.05
    _FRAME
    -0.05
    åĿIJ
    -0.05
    .overflow
    -0.05
    =======
    -0.05
     خاطر
    -0.04
     kom
    -0.04
    éĤ£äºĽ
    -0.04
    POSITIVE LOGITS
    æľīæѤ
    0.07
    ä¸Ńè¡Į
    0.06
    èĨ
    0.06
    æľīè¿Ļ个
    0.06
    vae
    0.06
    åŃ
    0.06
    æİĴåIJį第
    0.06
     potr
    0.06
    æĻ°
    0.05
    @email
    0.05
    Activations Density 0.001%

    No Known Activations