© 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. 17414
    Prev
    Next
    INDEX
    Explanations

    first words

    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
    çĽĴ
    -0.06
    æłĩå¿ĹçĿĢ
    -0.06
    antemente
    -0.06
    åºı
    -0.06
    æĹ©
    -0.06
    lessly
    -0.06
    çļĦä¸Ģ天
    -0.05
    éĴŁå£°
    -0.05
     ÙĪÙĤبÙĦ
    -0.05
    èĮħ
    -0.05
    POSITIVE LOGITS
    ä¸Ĭ大
    0.06
    iencia
    0.06
    uss
    0.06
    工大
    0.06
    ience
    0.06
    pii
    0.06
    pec
    0.06
    ÙĦÙĪ
    0.05
    cr
    0.05
    åħ·ä½ĵåĪĨæŀIJ
    0.05
    Activations Density 0.014%

    No Known Activations