© 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. 21551
    Prev
    Next
    INDEX
    Explanations

    than others

    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
    è¿Ļæľ¬
    -0.06
    åĴĮå¸Ĥ
    -0.05
    ذب
    -0.05
    ä¸įå·²
    -0.05
    ãĤ³ãĥŃ
    -0.05
    æ´»è·ĥçļĦ
    -0.05
    -active
    -0.05
    à¸ŀิ
    -0.05
    ä¸Ķ
    -0.05
    Ø·Ùģ
    -0.05
    POSITIVE LOGITS
     am
    0.05
    ox
    0.05
    olson
    0.05
    oc
    0.05
    æ®ĭä½Ļ
    0.05
     Creme
    0.05
     composed
    0.05
    欺éªĹ
    0.05
     pedido
    0.05
     cvs
    0.05
    Activations Density 0.002%

    No Known Activations