© 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. 19840
    Prev
    Next
    INDEX
    Explanations

    humble, modest, humility

    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
    uncul
    -0.06
    åĪĨæĶ¯
    -0.06
    æµ·æ£ł
    -0.05
    اÙĩد
    -0.05
    çķĻå®Ī
    -0.05
    çıĤ
    -0.05
    jde
    -0.05
     branching
    -0.05
    branch
    -0.05
     Branch
    -0.05
    POSITIVE LOGITS
     humility
    0.08
    è°¦èĻļ
    0.08
     humble
    0.07
     humild
    0.07
    è°¦éĢĬ
    0.07
    è°¦
    0.07
     khiêm
    0.07
    alu
    0.07
     modest
    0.06
     ÑģкÑĢом
    0.06
    Activations Density 0.010%

    No Known Activations