© 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. 17641
    Prev
    Next
    INDEX
    Explanations

    modal verbs followed by have/contain

    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
    zysta
    -0.06
    ائدة
    -0.06
    egni
    -0.06
    é¡¹çĽ®çļĦ建设
    -0.06
    lera
    -0.05
    벨
    -0.05
    æī¾åĪ°äºĨ
    -0.05
    egative
    -0.05
     Bela
    -0.05
     اÙĦشارع
    -0.05
    POSITIVE LOGITS
    åħ·
    0.06
    !/
    0.06
    æķħä½ľ
    0.06
    æĤ£
    0.05
    ro
    0.05
    æĥħåĨµçļĦ
    0.05
    ju
    0.05
    uah
    0.05
    اÙĦا
    0.05
    åıĪä½ķ
    0.05
    Activations Density 0.005%

    No Known Activations