© 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. 17944
    Prev
    Next
    INDEX
    Explanations

    after noun / is / rate / not null

    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
    à¸Ľà¸£
    -0.06
     vorbei
    -0.06
    vida
    -0.06
    åĪ«è¯´
    -0.05
    pragma
    -0.05
    Ñĥма
    -0.05
    ÑģпоÑģобноÑģÑĤÑĮ
    -0.05
    ÑģÑĤеÑģÑĤвенно
    -0.05
    irc
    -0.05
    works
    -0.05
    POSITIVE LOGITS
     ÙģØ¥ÙĨ
    0.06
    )).
    0.06
     being
    0.05
     inv
    0.05
    )}.
    0.05
    çĤ¹ãģ¯
    0.05
    ")).
    0.05
    è¿Ļæĺ¯
    0.05
    ").
    0.05
     Raja
    0.05
    Activations Density 0.206%

    No Known Activations