© 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. 19864
    Prev
    Next
    INDEX
    Explanations

    call or email someone

    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
    an
    -0.06
    vecs
    -0.06
    ichel
    -0.05
     nhan
    -0.05
    ÙĪز
    -0.05
    uebas
    -0.05
    è¿«ä¸įåıĬå¾ħ
    -0.05
    大åIJĥä¸ĢæĥĬ
    -0.05
     ÙĨØ´
    -0.05
    åīįåįĬ
    -0.05
    POSITIVE LOGITS
    ãĤŀ
    0.06
    å°Ĩæķ´ä¸ª
    0.06
    åľ°å°Ĩ
    0.06
    åĪĻå°Ĩ
    0.06
    å½Ĵ纳
    0.05
    表
    0.05
    缴çļĦ
    0.05
    åįģäºĮæĮĩ
    0.05
     equ
    0.05
    iku
    0.05
    Activations Density 0.001%

    No Known Activations