© 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. 20624
    Prev
    Next
    INDEX
    Explanations

    guarantee pledges willingness

    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
     Cast
    -0.06
    hazi
    -0.06
    awan
    -0.06
    èµIJ
    -0.05
     cast
    -0.05
    avn
    -0.05
    aille
    -0.05
    пиÑģÑĮ
    -0.05
    Hint
    -0.05
     form
    -0.05
    POSITIVE LOGITS
     pledges
    0.06
    ä¿Ŀè¯ģ
    0.06
     Guarantee
    0.06
    åı¯ä»¥ä¿Ŀè¯ģ
    0.06
    çļĦä¿Ŀè¯ģ
    0.06
    åĨ³ä¸į
    0.06
    ebed
    0.06
    ä¿ĿèŃī
    0.06
    ç»ĻçĶ¨æĪ·
    0.06
     guarantee
    0.06
    Activations Density 0.049%

    No Known Activations