© 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. 17044
    Prev
    Next
    INDEX
    Explanations

    killed

    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
    å·¥
    -0.06
    票
    -0.05
    åħµ
    -0.05
    åĩıéĢĢ
    -0.05
    Wil
    -0.05
    åĪĨ享
    -0.05
    ä¸Ģæĸ¹éĿ¢
    -0.05
    ä¸ĢåĪĩ
    -0.05
    éĢĢ
    -0.05
    _
    -0.04
    POSITIVE LOGITS
    egel
    0.07
     TRAS
    0.07
    /Error
    0.07
    illion
    0.06
    ä¸Ń游
    0.06
    éĶĻ误æĪĸ
    0.06
    igrams
    0.06
    fras
    0.06
    个篮æĿ¿
    0.06
    ())[
    0.06
    Activations Density 0.078%

    No Known Activations