© 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. 20026
    Prev
    Next
    INDEX
    Explanations

    is/been followed by passive verbs

    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
    jt
    -0.06
     rever
    -0.05
    éĢ¾è¶Ĭ
    -0.05
    pc
    -0.05
    éĤ£æĪijå°±
    -0.05
    nte
    -0.05
     yt
    -0.05
    vu
    -0.05
    OTT
    -0.05
     specifications
    -0.05
    POSITIVE LOGITS
    并ä¸įæĺ¯
    0.06
    å·¥ä½ľåĪ¶
    0.06
    ÃŃna
    0.06
    宿
    0.06
    对çħ§
    0.06
    èĻ½çĦ¶ä¸įæĺ¯
    0.05
    并éĿŀ
    0.05
    док
    0.05
    ilst
    0.05
    grounds
    0.05
    Activations Density 0.001%

    No Known Activations