© 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. 18033
    Prev
    Next
    INDEX
    Explanations

    body or bodies

    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
    èµ°åĪ°
    -0.05
     whose
    -0.05
    æĶ¶
    -0.05
    ocrat
    -0.05
    alcon
    -0.05
    alli
    -0.05
    ầm
    -0.05
    ugen
    -0.05
    whose
    -0.05
    讨
    -0.05
    POSITIVE LOGITS
    -around
    0.07
    人次
    0.06
    çŃĴ
    0.06
    æł©
    0.06
    ç»ı审çIJĨæŁ¥æĺİ
    0.06
    otch
    0.06
    ãĤµãĥªãĥ¼
    0.06
     generalized
    0.06
    ode
    0.06
    hol
    0.06
    Activations Density 0.004%

    No Known Activations