© 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. 21340
    Prev
    Next
    INDEX
    Explanations

    **hypo- and hyper- states**

    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
    nek
    -0.06
    大头
    -0.05
    incon
    -0.05
    åĽłä¸ºè¿Ļ
    -0.05
    æĽĿ
    -0.05
    -machine
    -0.05
    quen
    -0.05
    edt
    -0.05
     fla
    -0.05
    atz
    -0.05
    POSITIVE LOGITS
    ãĤ·ãĥĥãĥĹ
    0.06
    çŃ¹
    0.06
    bra
    0.06
    aza
    0.05
    åIJĪæĪIJçļĦ
    0.05
    bÄĻd
    0.05
    álogo
    0.05
     credito
    0.05
    è¦ģ继ç»Ń
    0.05
    åħĥçİ°éĩij
    0.05
    Activations Density 0.042%

    No Known Activations