© 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. 20892
    Prev
    Next
    INDEX
    Explanations

    IP address resolution

    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
    bara
    -0.06
    èĴ¸èĴ¸
    -0.06
    带走
    -0.06
    anho
    -0.06
    -origin
    -0.06
    eam
    -0.05
    æĶ¾é¡Į
    -0.05
     xÆ°ng
    -0.05
    bre
    -0.05
    Ñģловно
    -0.05
    POSITIVE LOGITS
    uffle
    0.06
    es
    0.05
     Associates
    0.05
    allas
    0.05
     окÑĢÑĥг
    0.05
    æľĢåIJİè¿ĺæĺ¯
    0.05
     associ
    0.05
    olist
    0.05
    误导
    0.05
    ces
    0.05
    Activations Density 0.014%

    No Known Activations