© 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. 21552
    Prev
    Next
    INDEX
    Explanations

    `with` followed by descriptive adjectives

    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
    纵横
    -0.06
    éĽĨåĽ¢æĹĹä¸ĭ
    -0.06
    ei
    -0.06
    éĽĨåĽ¢
    -0.06
    ({},
    -0.06
    Manip
    -0.06
    à¤Ĺत
    -0.06
    éĽĨåĽ¢çļĦ
    -0.05
    elic
    -0.05
    uang
    -0.05
    POSITIVE LOGITS
     Bras
    0.06
    èĮĦ
    0.06
    åĬŁäºİ
    0.05
     Brotherhood
    0.05
    öre
    0.05
    å½ĴåĬŁäºİ
    0.05
    arca
    0.05
     bras
    0.05
    åį¯
    0.05
     initializer
    0.05
    Activations Density 0.001%

    No Known Activations