© 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. 17500
    Prev
    Next
    INDEX
    Explanations

    born in place

    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
     Ro
    -0.05
     Bal
    -0.05
    halter
    -0.05
    sver
    -0.05
    åľ¨éĩij
    -0.05
    åķ¡
    -0.05
    åĴĮåķĨä¸ļ
    -0.05
    çļĦæĺ¯
    -0.05
    peer
    -0.05
    ä¸įå¼Ģ
    -0.05
    POSITIVE LOGITS
    .$.
    0.07
    auta
    0.06
    دÙĬØ©
    0.06
    iht
    0.06
    amid
    0.06
    并ç»ĵåIJĪ
    0.06
     ÑģоÑĤ
    0.06
    ilus
    0.05
    .clf
    0.05
    unti
    0.05
    Activations Density 0.084%

    No Known Activations