© 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. 21529
    Prev
    Next
    INDEX
    Explanations

    tax and financial matters

    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
    зон
    -0.06
    对äºİè¿ĻäºĽ
    -0.06
    ital
    -0.06
    à¸Ńà¸ģ
    -0.06
    shal
    -0.05
    olver
    -0.05
    éĺ
    -0.05
    acc
    -0.05
    ãĥĪãĥ©
    -0.05
     Loud
    -0.05
    POSITIVE LOGITS
    elat
    0.06
    汽水
    0.06
    IGH
    0.06
    arly
    0.06
    .python
    0.05
    ØŃ
    0.05
    -role
    0.05
    ignes
    0.05
    æĢ§çŃī
    0.05
    éħĴåºĹ管çIJĨ
    0.05
    Activations Density 0.009%

    No Known Activations