© 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. 17472
    Prev
    Next
    INDEX
    Explanations

    digitalcommons.law.villanova.edu

    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
    以æĿ¥
    -0.05
    ers
    -0.05
     vent
    -0.05
    对æĸ¹
    -0.05
     guide
    -0.05
     reporting
    -0.05
    æĬ¥åijĬ
    -0.05
    wald
    -0.05
    产åīį
    -0.05
    åĽĬ
    -0.05
    POSITIVE LOGITS
    积æŀģæݨåĬ¨
    0.06
    downloads
    0.06
    rowse
    0.06
    มหา
    0.06
     voulais
    0.06
    UNKNOWN
    0.06
    iggins
    0.06
    æĶ¾é¡Į
    0.06
    ä½ķæĻĤ
    0.06
    cole
    0.06
    Activations Density 0.051%

    No Known Activations