© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20582
    Prev
    Next
    INDEX
    Explanations

    leads you, comfort to, little steps, broken nation

    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
    iri
    -0.06
    oj
    -0.06
    aira
    -0.06
    ÙĥرÙĬ
    -0.06
    ome
    -0.06
    çķĶ
    -0.06
    au
    -0.06
    inom
    -0.06
    ook
    -0.06
    meg
    -0.05
    POSITIVE LOGITS
    å¼ı
    0.07
    æĦıæĸĻ
    0.05
    à¸Ńà¸ĩ
    0.05
    cent
    0.05
    å¼ı设计
    0.05
    últ
    0.05
    alfa
    0.05
     cent
    0.05
    è§ĨçĤ¹
    0.05
    asper
    0.05
    Activations Density 0.010%

    No Known Activations